Blended Price
$10.00/M
Input Price
$5.00/M
Output Price
$25.00/M
Speed
—
TTFT
—
Hidden, no data: Output Speed
Axes
Filters
Providers
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-20
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-18
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-17
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-16
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-10
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-09
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-06
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-04
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-11-02
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-28
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-21
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-19
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-15
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-14
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-13
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-06
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-10-02
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-24
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-22
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-21
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-04
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-03
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-09-01
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-21
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-20
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-13
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-07
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-06
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-08-05
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-07-31
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-07-30
v3 · public-demo · Claude Opus 4.8 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-8-high
{
"provider": "Anthropic",
"modelType": "CoT",
"modelsUrl": "https://arcprize.org/media/data/models.json",
"modelGroup": "anthropic-opus-4-8",
"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-opus-4-8-high",
"environmentCount": 25,
"modelReleaseDate": "2026-06-01T00:00:00.000Z",
"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": 10000,
"providerModelIdPublished": false
}Evidence observed 2026-07-24
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-21
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-20
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-19
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-18
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-17
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-16
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-15
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-14
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-13
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-12
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-11
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-10
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-09
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-08
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-07
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-06
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-05
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-04
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-03
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-02
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-11-01
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-31
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-30
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-29
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-28
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-27
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-26
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-25
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-19
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-18
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-15
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-14
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-13
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-12
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-11
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-10
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-09
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 5,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-08
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-07
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-06
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-05
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-04
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-03
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-02
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-10-01
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-30
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-29
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-28
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-27
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-26
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-25
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-24
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-23
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-22
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-21
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-20
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-19
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-18
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-17
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-16
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-15
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-14
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-13
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-12
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-11
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-10
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-09
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-08
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-07
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-06
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-05
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-04
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-03
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-02
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-09-01
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-31
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-30
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-29
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-28
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-27
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-26
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-25
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-24
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-23
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-22
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-21
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-20
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-19
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-18
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-17
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-16
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-15
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-14
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-13
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-12
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-11
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-10
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-09
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-08
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-07
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-06
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-05
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-04
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-03
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-02
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-08-01
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-07-31
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-07-30
vlive-leaderboard · enigma_eval · claude-opus-4-8-xhigh · effort xhigh · 1 attempt · pass@1 · scale-seal · provider claude-opus-4-8-xhigh · record enigma_eval:claude-opus-4-8-xhigh
{
"rank": 4,
"company": "anthropic",
"benchmarkId": "enigma_eval",
"identityNote": "Scale SEAL published configuration label preserved",
"benchmarkName": "EnigmaEval"
}Evidence observed 2026-07-29
v2026.06 · official-100-task · Claude Opus 4.8 (max) · harness mini-swe-agent · effort max · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider anthropic/claude-opus-4-8 · record opus-48-mini-swe · run 4ee23dca8f25cd97660a6a5e6781ba4c8a820780bc8018dd43fcf22a96c06b11
{
"taskCount": 100,
"agentGroup": "mini-swe-agent:claude-opus-4-8",
"basicPassAt1": 39.77272727272727,
"datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
"publicTaskCount": 50,
"tastefulPassAt1": 25,
"agentDescription": "Claude Opus 4.8 via mini-swe-agent harness (Portkey→Bedrock)",
"privateTaskCount": 50,
"upstreamProvider": "anthropic",
"upstreamRunCount": 80,
"averageAgentSteps": 132.36363636363637,
"averageOutputTokens": 115169.26136363637,
"averageTotalCostUsd": 8.03432186590909,
"averageOutputCostUsd": 2.879231534090909
}Evidence observed 2026-06-30
vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · Claude Opus 4.8-xhigh · harness swe-rebench-react@tools · effort xhigh · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Claude Opus 4.8-xhigh__tools · record Claude Opus 4.8-xhigh__tools:1772323200000:1778803200000
{
"passAt5": 67.27272727272727,
"developer": "anthropic",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2479387.470909091,
"modelReleaseDate": "2026-05-28",
"scoreStandardError": 1.199173268933903,
"cachedTokenPercentage": 95.27838279131717,
"modelReleaseTimestamp": 1779926400000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 2.0202793086363635,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
},
"publishedTaskRangeTimestamp": {
"to": 1778803200000,
"from": 1772323200000
}
}Evidence observed 2026-05-15
v2.1 · official-leaderboard · Opus 4.8 (high) · harness [email protected] · effort high · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider anthropic/claude-opus-4-8 · record leaderboard/submissions/2026-07-09-anthropic-claude-opus-4-8-high-claude-code.json · run a3019ec2-bc78-5ff6-9cae-d22d62470515
{
"passAt2": 0.8652,
"passAt3": 0.9011,
"passAt4": 0.9258,
"passAt5": 0.9438,
"taskCount": 89,
"actualTokens": {
"output": 8089069,
"cachedInput": 161931526,
"uncachedInput": 12873472
},
"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/92",
"agentDisplayUrl": "https://claude.com/claude-code",
"modelDisplayUrl": "https://www.anthropic.com/news/claude-opus-4-8",
"actualTrialCount": 445,
"agentOrganization": "Anthropic",
"modelOrganization": "Anthropic",
"actualTotalCostUsd": 286.94,
"rewardHacksPercent": 0,
"accuracyStandardError": 1.31,
"submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-07-09-anthropic-claude-opus-4-8-high-claude-code.json",
"disqualifiedTrialCount": 0,
"expectedAttemptsPerTask": 5,
"sourceFilterReasoningEffort": "high",
"actualAverageTrialDurationSeconds": 551.4
}Evidence observed 2026-07-09