Blended Price
$3.00/M
Input Price
$2.00/M
Output Price
$6.00/M
Speed
—
TTFT
—
Hidden, no data: AgMoBench Agentic, Output Speed
Axes
Filters
Providers
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-18
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-18
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-18
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-17
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-17
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-17
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-16
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-16
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-16
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-10
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-10
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-10
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-09
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-09
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-09
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-06
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-06
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-06
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-04
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-04
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-04
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-11-02
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-11-02
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-11-02
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-28
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-28
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-28
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-21
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-21
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-21
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-19
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-19
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-19
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-15
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-15
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-15
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-13
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-13
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-13
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-06
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-06
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-06
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-02
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-02
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-02
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-10-01
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-10-01
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-10-01
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-30
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-30
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-30
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-29
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-29
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-29
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-28
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-28
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-28
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c985e4804ffc840374d9852c6b60005c\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0a820529c69911b0c1a63d8b2d3dbf0f\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-21
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c985e4804ffc840374d9852c6b60005c\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0a820529c69911b0c1a63d8b2d3dbf0f\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-21
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"c985e4804ffc840374d9852c6b60005c\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0a820529c69911b0c1a63d8b2d3dbf0f\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-21
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-04
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-04
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-04
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-03
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-03
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-03
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"07d05a64baf8bd11a2e8505b7f9a1cc0\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4cf045387256dca83a7f8275d8d2157b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-09-01
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"07d05a64baf8bd11a2e8505b7f9a1cc0\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4cf045387256dca83a7f8275d8d2157b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-09-01
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"07d05a64baf8bd11a2e8505b7f9a1cc0\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4cf045387256dca83a7f8275d8d2157b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-09-01
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3a9d42354f8128c11c15f5932e4a2fc7\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a865a80739604261a4cb1abb00b293d4\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-21
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3a9d42354f8128c11c15f5932e4a2fc7\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a865a80739604261a4cb1abb00b293d4\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-21
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"3a9d42354f8128c11c15f5932e4a2fc7\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a865a80739604261a4cb1abb00b293d4\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-21
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"04f6ba019798e7ba90a11d7da82ed138\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"8f93bcbb2793025d982217c174632a0c\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-13
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"04f6ba019798e7ba90a11d7da82ed138\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"8f93bcbb2793025d982217c174632a0c\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-13
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"04f6ba019798e7ba90a11d7da82ed138\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"8f93bcbb2793025d982217c174632a0c\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-13
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"1c13f7ca05a41dddb3e8dbf221993d7e\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a339ccee4fdf8453a492fc58c884889b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-07
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"1c13f7ca05a41dddb3e8dbf221993d7e\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a339ccee4fdf8453a492fc58c884889b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-07
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"1c13f7ca05a41dddb3e8dbf221993d7e\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a339ccee4fdf8453a492fc58c884889b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-07
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"6bd4d2a79abbba43993aa72466c90f28\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"909105c66efc7bcdbd1ddf40343ec110\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-06
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"6bd4d2a79abbba43993aa72466c90f28\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"909105c66efc7bcdbd1ddf40343ec110\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-06
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"6bd4d2a79abbba43993aa72466c90f28\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"909105c66efc7bcdbd1ddf40343ec110\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-06
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"fe316c967e356fc8f0ae7405b6a374ea\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1102d97f1e4c2cf4cd67b86832b6396b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-08-05
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"fe316c967e356fc8f0ae7405b6a374ea\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1102d97f1e4c2cf4cd67b86832b6396b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-08-05
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"fe316c967e356fc8f0ae7405b6a374ea\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1102d97f1e4c2cf4cd67b86832b6396b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-08-05
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-07-30
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-07-30
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-07-30
v3 · public-demo · Grok 4.5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-high
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
"upstreamModelId": "xai-grok-4-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 6892.87,
"providerModelIdPublished": false
}Evidence observed 2026-07-24
v3 · public-demo · Grok 4.5 (Medium) · effort medium · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-medium
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
"upstreamModelId": "xai-grok-4-5-medium",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8458.3,
"providerModelIdPublished": false
}Evidence observed 2026-07-24
v3 · public-demo · Grok 4.5 (Low) · effort low · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:xai-grok-4-5-low
{
"provider": "xAI",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "xai-grok-4-5",
"modelNotes": null,
"modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
"upstreamModelId": "xai-grok-4-5-low",
"environmentCount": 25,
"modelReleaseDate": "2026-07-16T00:00:00.000Z",
"upstreamDatasetId": "v3_Semi_Private",
"actionBudgetPolicy": "5x-human-baseline-median-per-level",
"technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
"catalogMatchAliases": [],
"agentHarnessPublished": false,
"verificationAuthority": "ARC Prize Foundation",
"upstreamRunIdPublished": false,
"actualEvaluationCostUsd": 8718.48,
"providerModelIdPublished": false
}Evidence observed 2026-07-24
vv0.1.0@eb4af26c249b5770e788aa9e3acd2f6ef21f50c2 · official-leaderboard · Grok 4.5 (xhigh) · harness Cursor CLI · effort xhigh · 1 attempt · harbor:frontier-bench/frontier-bench@2f325140-b410-452e-87b3-978ffcb4e1ea · record 2ccf029d-62fe-4756-a624-b2d376895a32
{
"taskCount": 74,
"metricName": "accuracy",
"releaseTag": "v0.1.0",
"agentDisplay": {
"url": "https://cursor.com/docs/cli/overview",
"label": "Cursor CLI"
},
"modelDisplay": {
"url": "https://docs.x.ai/developers/models/grok-4.5",
"label": "Grok 4.5"
},
"rowCreatedAt": "2026-07-23T00:49:01.181248+00:00",
"rowUpdatedAt": "2026-07-28T19:49:06.124157+00:00",
"leaderboardId": "076032b9-6e20-458a-b56d-5aea2488b3f9",
"releaseCommit": "eb4af26c249b5770e788aa9e3acd2f6ef21f50c2",
"datasetPackage": "frontier-bench/frontier-bench",
"evaluationDate": "2026-07-15",
"attemptsPerTask": 1,
"leaderboardRank": 6,
"metricSemantics": "native-harbor-accuracy-not-pass-at-k",
"datasetVersionId": "2f325140-b410-452e-87b3-978ffcb4e1ea",
"measurementScope": "model-agent-system",
"modelReleaseDate": "2026-07-08",
"actualTotalTokens": 1238993118,
"agentOrganization": {
"url": "https://cursor.com",
"label": "Cursor"
},
"agmobenchEligible": false,
"leaderboardStatus": "display",
"modelOrganization": {
"url": "https://x.ai",
"label": "xAI"
},
"actualTotalCostUsd": 960.04,
"attemptsProvenance": "frontier-bench-v0.1-official-command-uses-harbor-default",
"upstreamTrialCount": 0,
"accuracyStandardError": 1.47,
"attemptsProvenanceUrls": [
"https://github.com/harbor-framework/frontier-bench/blob/eb4af26c249b5770e788aa9e3acd2f6ef21f50c2/README.md#running-the-benchmark",
"https://github.com/harbor-framework/harbor/blob/v0.14.0/src/harbor/models/job/config.py#L318-L323"
]
}Evidence observed 2026-07-23
v2026.06 · official-100-task · Grok 4.5 (high) · harness mini-swe-agent · effort high · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider openai/grok-4.5 · record grok-4-5-mini-swe · run 1b426ea2b95513900b31967c6460a77b395f178aced1c84f631044114146fd16
{
"taskCount": 100,
"agentGroup": "mini-swe-agent:grok-4.5",
"basicPassAt1": 49.42528735632184,
"datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
"publicTaskCount": 50,
"tastefulPassAt1": 17.24137931034483,
"agentDescription": "xAI Grok 4.5 via mini-swe-agent harness (Portkey→xAI)",
"privateTaskCount": 50,
"upstreamProvider": "xai",
"upstreamRunCount": 50,
"averageAgentSteps": 79.86363636363636,
"averageOutputTokens": 22893.670454545456,
"averageTotalCostUsd": 1.2253361936363636,
"averageOutputCostUsd": 0.13736202272727271
}Evidence observed 2026-07-09
vcontinuous-leaderboard · tasks-created:2026-05-15:2026-07-01 · Grok 4.5 [high] · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Grok 4.5 [high]__tools · record Grok 4.5 [high]__tools:1778803200000:1782864000000
{
"passAt5": 77.47747747747748,
"developer": "xai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2429423.823423424,
"modelReleaseDate": "2026-07-08",
"scoreStandardError": 0.5975900523162895,
"cachedTokenPercentage": 92.59017890332878,
"modelReleaseTimestamp": 1783468800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.4705187747747748,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
}
}Evidence observed 2026-07-01
vcontinuous-leaderboard · tasks-created:2026-05-15:2026-07-01 · Grok 4.5 [high] · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Grok 4.5 [high]__tools · record Grok 4.5 [high]__tools:1778803200000:1782864000000
{
"passAt5": 77.47747747747748,
"developer": "xai",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2429423.823423424,
"modelReleaseDate": "2026-07-08",
"scoreStandardError": 0.5975900523162895,
"cachedTokenPercentage": 92.59017890332878,
"modelReleaseTimestamp": 1783468800000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 1.4705187747747748,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
}
}Evidence observed 2026-07-01
v2.1 · official-leaderboard · Grok 4.5 (high) · harness [email protected] · effort high · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider cursor/grok-4.5 · record leaderboard/submissions/2026-07-09-cursor-grok-4-5-none-cursor-cli.json · run d478d2af-5348-575c-b20a-e5a2434dbff7
{
"passAt2": 0.8888,
"passAt3": 0.9236,
"passAt4": 0.9416,
"passAt5": 0.9551,
"taskCount": 89,
"actualTokens": {
"output": 4734062,
"cachedInput": 161079936,
"uncachedInput": 12570445
},
"datasetPackage": "terminal-bench/terminal-bench-2-1",
"leaderboardUrl": "https://www.tbench.ai/leaderboard/terminal-bench/2.1",
"pullRequestUrl": "https://github.com/harbor-framework/terminal-bench-2-1/pull/86",
"agentDisplayUrl": "https://cursor.com/docs/cli/overview",
"modelDisplayUrl": "https://docs.x.ai/developers/models/grok-4.5",
"actualTrialCount": 445,
"agentOrganization": "Cursor",
"modelOrganization": "xAI",
"actualTotalCostUsd": 134.09,
"rewardHacksPercent": 8.99,
"accuracyStandardError": 1.46,
"submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-07-09-cursor-grok-4-5-none-cursor-cli.json",
"disqualifiedTrialCount": 40,
"expectedAttemptsPerTask": 5,
"sourceFilterReasoningEffort": null,
"actualAverageTrialDurationSeconds": 443
}Evidence observed 2026-07-09