Blended Price
$10.00/M
Input Price
$5.00/M
Output Price
$25.00/M
Speed
—
TTFT
—
Hidden, no data: AgMoBench Math, AgMoBench Agentic, AgMoBench Robustness, Output Speed
Axes
Filters
Providers
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.36924,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.36924,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-18
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-17
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-16
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-10
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-09
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-06
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-04
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-11-02
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-28
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-21
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-19
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-15
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-13
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-06
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-02
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-10-01
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"8bfe2e142f29acec39df406a6631f81a\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"92bfaa47028eae49163960f4c5a298a0\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-30
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"16793624264c3bdded076b4e26af5a90\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"e7fb37556a7353e7da435c4c7b78ca50\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-29
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"284ac3aff89a7d8a3aca179ee1e5dd61\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6e0849a05a2c572b1050e5900a372e2b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-28
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"c985e4804ffc840374d9852c6b60005c\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0a820529c69911b0c1a63d8b2d3dbf0f\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-21
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-04
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-03
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"07d05a64baf8bd11a2e8505b7f9a1cc0\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"4cf045387256dca83a7f8275d8d2157b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-09-01
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"3a9d42354f8128c11c15f5932e4a2fc7\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a865a80739604261a4cb1abb00b293d4\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-21
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"04f6ba019798e7ba90a11d7da82ed138\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"8f93bcbb2793025d982217c174632a0c\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-13
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"1c13f7ca05a41dddb3e8dbf221993d7e\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"a339ccee4fdf8453a492fc58c884889b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-07
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"6bd4d2a79abbba43993aa72466c90f28\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"909105c66efc7bcdbd1ddf40343ec110\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-06
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"fe316c967e356fc8f0ae7405b6a374ea\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"1102d97f1e4c2cf4cd67b86832b6396b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-08-05
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-07-30
v3 · public-demo · Claude Opus 5 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-claude-opus-5-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-claude-opus-5",
"modelNotes": "Evaluation conducted with 'high' output effort.",
"modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
"scoreMetric": "relative-human-action-efficiency",
"evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
"evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
"upstreamModelId": "anthropic-claude-opus-5-high",
"environmentCount": 25,
"modelReleaseDate": "2026-07-24T00:00:00.000Z",
"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": 20657.37,
"providerModelIdPublished": false
}Evidence observed 2026-07-24
vcontinuous-leaderboard · tasks-created:2026-05-15:2026-07-01 · Opus 5 [high] · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Opus 5 [high]__tools · record Opus 5 [high]__tools:1778803200000:1782864000000
{
"passAt5": 74.77477477477478,
"developer": "anthropic",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 4322143.001801802,
"modelReleaseDate": "2026-07-24",
"scoreStandardError": 1.35435102507864,
"cachedTokenPercentage": 95.70555353401815,
"modelReleaseTimestamp": 1784851200000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 3.4657367509009007,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
},
"publishedTaskRangeTimestamp": {
"to": 1782864000000,
"from": 1778803200000
}
}Evidence observed 2026-07-01