AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Models

Claude Opus 4.7

Anthropic's most capable generally available model. Step-change in agentic coding, stronger vision (3.75MP), long-context reasoning, and knowledge work.

April 16, 2026Last synced Nov 22, 2026, 8:17 AM1000K context128K output
Effort
  • Default
  • High (non-reasoning)
  • Max

Blended Price

$10.00/M

Input Price

$5.00/M

Output Price

$25.00/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

Performance Radar

Claude Opus 4.7
Field Average

Hidden, no data: AgMoBench Overall, AgMoBench Reasoning, AgMoBench Coding, AgMoBench Math, AgMoBench Agentic, AgMoBench Robustness, Output Speed

* Shared benchmarks shown in their place: GPQA Diamond, HLE, ARC-AGI-2, Terminal-Bench Hard

External Benchmarks

GPQA Diamond

How Claude Opus 4.7 Compares

Axes

Filters

$0.00 – $67.5
≥ 1.4

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu
openai
zai
meta
nvidia
xai
upstage
deepseek
alibaba
mistral
nous-research
aws
google
anthropic
xiaomi
stepfun
kimi
reflection
minimax
azure
inclusionai
reka-ai
cohere
bytedance_seed
inception
tencent
thinking-machines
Bubble size = Context Window
8191.00
2000000.00
Compare with other models
—
Coding Index
—
Math Index
—
MMLU Pro
— / 100
GPQA Diamond
94.2 / 100
HLE
46.9 / 100
LiveCodeBench
— / 100
SciCode
— / 100
MATH-500
— / 100
AIME
— / 30
AIME 2025
— / 30
IFBench
— / 100
LCR
— / 100
Terminal-Bench Hard
69.4 / 100
τ²-Bench
— / 100
aa
94.2 / 100
HLEaa
46.9 / 100
Terminal-Bench Hardaa
69.4 / 100
AA-Omniscience Accuracyaa_omniscience
43.5 / 100
AA-Omniscience Indexaa_omniscience
26.2 / 100
Aider Polyglotaider
72.0 / 100
CharXiv Reasoning (no tools)anthropic_launch
82.1 / 100
CharXiv Reasoning (with tools)anthropic_launch
91.0 / 100
CyberGymanthropic_launch
73.1 / 100
Finance Agent v1.1anthropic_launch
64.4 / 100
HLE (with tools)anthropic_launch
54.7 / 100
ARC-AGI-1arc_agi
22.5 / 100
ARC-AGI-1 Cost per Taskarc_agi
0.4
ARC-AGI-2arc_agi
1.3 / 100
ARC-AGI-2 Cost per Taskarc_agi
0.6
ARC-AGI-1benchmark_matrix
35.7 / 100
ARC-AGI-2benchmark_matrix
8.6 / 100
AIME 2024benchmark_matrix
75.5
AIME 2025 (Matrix)benchmark_matrix
90.0
Arena-Hard Autobenchmark_matrix
59.7
BrowseCompbenchmark_matrix
79.3
Codeforces Ratingbenchmark_matrix
1886.0
CritPtbenchmark_matrix
0.3
GPQA Diamond (Matrix)benchmark_matrix
83.3
HLE (Matrix)benchmark_matrix
7.1
HMMT Feb 2025benchmark_matrix
15.9
IFEvalbenchmark_matrix
89.7
LiveCodeBench (Matrix)benchmark_matrix
47.4
MATH-500 (Matrix)benchmark_matrix
94.4
MMLUbenchmark_matrix
88.8
MMLU-Pro (Matrix)benchmark_matrix
86.6
OSWorld (Unversioned Matrix Import)benchmark_matrix
38.2 / 100
SWE-bench Probenchmark_matrix
35.8
Terminal-Bench 2.0benchmark_matrix
43.2
Terminal-Bench 1.0benchmark_matrix
39.0
FrontierMathbenchmark_matrix
10.0 / 100
MMMUbenchmark_matrix
76.5 / 100
simpleqabenchmark_matrix
22.8
SWE-bench Verifiedbenchmark_matrix
79.4 / 100
tau-bench Retailbenchmark_matrix
81.4 / 100
BullshitBenchbullshitbench
83.0 / 100
Arena ELO: Codingchatbot_arena
1557.0
Arena ELO: Creative Writingchatbot_arena
1494.0
arena_elo_documentchatbot_arena
1496.0
Chatbot Arena ELOchatbot_arena
1490.0
arena_elo_searchchatbot_arena
1230.0
arena_elo_visionchatbot_arena
1317.0
Cybenchcybench
96.0
Aider Polyglotepoch_ai
0.3
Ale Benchepoch_ai
1323.0
Algotuneepoch_ai
1.3
Apex Agentsepoch_ai
3.5
Arc Agi 2epoch_ai
0.6
Blueprint Bench 2epoch_ai
0.2
Chess Puzzlesepoch_ai
0.3
Critptepoch_ai
0.1
Cursorbenchepoch_ai
0.5
CyBenchepoch_ai
0.4
DeepResearchBenchepoch_ai
0.5
Eci Scoresepoch_ai
158.5
Enigma Evalepoch_ai
0.1
Epoch Capabilities Indexepoch_ai
156.1
Exploitbenchepoch_ai
0.2
FictionLiveBenchepoch_ai
0.6
Forecastbenchepoch_ai
62.4
Frontiercodeepoch_ai
0.4
Frontiersweepoch_ai
8.3
Gbaevalepoch_ai
0.4
Gdp Pdfepoch_ai
0.2
GeoBenchepoch_ai
0.0
GSOepoch_ai
0.4
Hleepoch_ai
0.4
Lech Mazur Writingepoch_ai
8.3
METR Time Horizonsepoch_ai
20.4
Mirrorcodeepoch_ai
0.3
Mystery Game Puzzlesepoch_ai
0.1
OSWorld 2.0 (Epoch Import)epoch_ai
500.0 / 100
OTIS Mock AIME 2024–2025epoch_ai
1.0
Posttrainbenchepoch_ai
0.2
Processed Data For Eciepoch_ai
0.2
Proofbenchepoch_ai
0.5
Scicodeepoch_ai
0.5
SimpleQA Verified (Epoch)epoch_ai
0.5
Vending Bench 2epoch_ai
10936.8
VPCTepoch_ai
0.3
WebDev Arenaepoch_ai
1555.2
EQ-Bench 3eqbench
1461.0
FrontierMathfrontiermath
43.8 / 100
LegalBenchlegalbench
85.3 / 100
AIME 2026matharena
95.8
MMMUmmmu
76.5 / 100
OpenRouter Token Volumeopenrouter_rankings
589000000000.0
OpenRouter Weekly Trendopenrouter_rankings
70.0
MCP Atlasseal
79.1
SimpleBenchsimplebench
61.7 / 100
SWE-bench Verifiedswebench
87.6 / 100
Vectara Factual Consistencyvectara_hallucination
88.0 / 100
Vectara Hallucination Ratevectara_hallucination
12.0 / 100
WeirdMLweirdml
75.5 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"ec09fbed9f211f59ec54cca2227c3309\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5814b0938ba4a54ba31da46fe17d4380\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"d8dfdc9958a2e1502b54603b03fbc557\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"aaa10807f3dcaae3ce6c15be7539e733\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-20

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-18

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"f4d8307b32b2fefe010860bedd0c5dd8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef15ebd7644a875688eda094d716da9a\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-17

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"69aae253e532553a920bf4deb50ca495\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"5206202f381a21893de82dcc2db93ae9\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-16

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"513aaaa353972ca0baa9c95cb95e04dd\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"169653a17d103c8dbca682167ffccaa6\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-10

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"3d7dcca4fb88130b9e7ec186fd9ae23f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"1e46e6ab8c83fb1a7b19f10be398adf2\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-09

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"8ea4d2292a0a8c759aa7e80a2041122d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"94fd3d68aacca744ff3c39f63a187685\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-06

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-04

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"c4baed683b2f33c40537f2338682475f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"48d1fd5bf96ae9583213f6699f12f2cc\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-11-02

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"8fc20a5217998d26c40ad2306d648194\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"095b2fa20aac96121092dab07e18cc8e\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-28

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"400b32b66e8c1b37fc50ff586b033048\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9314d4bea0d9d001c69a11614dc8d93c\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-21

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"2ab08f641c16bcf3c7a59c38b35fa2e3\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"b4ed41aee6b00420557f098bd05f4165\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-19

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"8cf5cb76df0b13c1684b346a2012df83\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"c6e9a78d12dc070d7dab18a1f667a410\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-15

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"57cc4a7689e563a0ffb7d275eb3a889b\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"19d71f8c9a2056c0be4bb4fd4a75a325\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-14

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"e7f673a6db195dac7f2956e3b1651145\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"4d3b46c6ffe9404ca1c0ebcfb5938883\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-13

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"b57a26ca4df83acaa40eadb6632c7c61\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ee35c9dbbb033dc7de85467eedb85d54\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-06

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"b52a6e82589fb2c719168d69aa0bb015\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f187ceaff4d7f6156e77c1f1254aafc8\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-10-02

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"397d7634d348db2ae8df5180db7b475d\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"882404aedf04dbdde2b6c0d731212a4f\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-24

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"58c953e3f78e2282d0259b52304c8ef8\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"ef004f05f102510151398f73e966a509\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-22

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"2f3beadbd513a221b41d3816ff651f54\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"f1d0d3b7e367e4a7909882624b1caca0\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-22

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"c985e4804ffc840374d9852c6b60005c\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"0a820529c69911b0c1a63d8b2d3dbf0f\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-21

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-04

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"a8dc9c600e07efa11ca8fb622181783f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"946807139d47f4bc368591b95885dfb4\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-03

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"07d05a64baf8bd11a2e8505b7f9a1cc0\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"4cf045387256dca83a7f8275d8d2157b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-09-01

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"3a9d42354f8128c11c15f5932e4a2fc7\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"a865a80739604261a4cb1abb00b293d4\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-21

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-20

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"a2c874a4c5dac6490bc20617a93e7b62\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"66731344a65b8943f176406bd6afd4bb\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-20

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"04f6ba019798e7ba90a11d7da82ed138\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"8f93bcbb2793025d982217c174632a0c\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-13

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"1c13f7ca05a41dddb3e8dbf221993d7e\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"a339ccee4fdf8453a492fc58c884889b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-07

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"6bd4d2a79abbba43993aa72466c90f28\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"909105c66efc7bcdbd1ddf40343ec110\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-06

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"fe316c967e356fc8f0ae7405b6a374ea\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"1102d97f1e4c2cf4cd67b86832b6396b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-08-05

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-31

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-31

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-30

0.2 / 100
ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · Opus 4.7 (High) · effort high · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:anthropic-opus-4-7-high

View run source

Source metadata
{
  "provider": "Anthropic",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "anthropic-opus-4-7",
  "modelNotes": null,
  "modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
  "upstreamModelId": "anthropic-opus-4-7-high",
  "environmentCount": 25,
  "modelReleaseDate": "2026-04-16T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [
    "claude-opus-4-7"
  ],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 10000,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-24

0.2 / 100
ExploitGym v1exploitgym

[email protected]@dcdbc88cbef13624328cc6d059a007a5d29b3c00 · official-869-task · Claude Opus 4.7 · harness Claude Code · 1 attempt · 2h timeout · exploitgym:[email protected]@dcdbc88cbef13624328cc6d059a007a5d29b3c00:869-tasks · record exploitgym:v1:parent:f2e71c804e6d6d491550d4d9db597f11627d924f7f34acbdcb0fee9ace3a4f97

Preliminary

View run source

Source metadata
{
  "taskCount": 869,
  "harnessTag": "v1.1.1",
  "metricName": "agmodbDerivedOnTargetPercent",
  "taskListUrl": "https://github.com/sunblaze-ucb/exploitgym/blob/dcdbc88cbef13624328cc6d059a007a5d29b3c00/data/task_ids/v1.txt",
  "aggregateOnly": true,
  "onTargetCount": 12,
  "evaluationDate": "2026-06-16",
  "upstreamSource": "ExploitGym Team",
  "attemptsPerTask": 1,
  "benchmarkCommit": "dcdbc88cbef13624328cc6d059a007a5d29b3c00",
  "metricSemantics": "AgMoDB-derived on_target count divided by the fixed v1 task count",
  "aggregateVariant": "parent",
  "measurementScope": "model-agent-system",
  "agmobenchEligible": false,
  "attemptsSemantics": "one submitted result trial per benchmark task, not 869 attempts per task",
  "upstreamSourceUrl": null,
  "preliminaryReasons": [
    "missing-exact-agent-revision",
    "missing-upstream-run-identity"
  ],
  "evaluationCondition": "2h timeout",
  "domainOnTargetCounts": {
    "v8": 8,
    "kernel": 0,
    "userspace": 4
  },
  "attemptsProvenanceUrl": "https://github.com/sunblaze-ucb/exploitgym/blob/603efb3461d17ed05718ca778d2715db772d9385/docs/submission.md#resultsjson",
  "mitigatedOnTargetCounts": {
    "v8": 0,
    "kernel": 0,
    "userspace": 0
  },
  "submissionContractCommit": "603efb3461d17ed05718ca778d2715db772d9385",
  "exactReproductionEligible": false
}

Evidence observed 2026-06-16

1.4 / 100
Senior SWE-Bench v2026.06senior_swe_bench

v2026.06 · official-100-task · Claude Opus 4.7 (max) · harness mini-swe-agent · effort max · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider anthropic/claude-opus-4-7 · record opus-mini-swe · run 1d69314975a9519f64c507748d04762ded7853ebf34982811a94ac3a27ba2f9e

View run source

Source metadata
{
  "taskCount": 100,
  "agentGroup": "mini-swe-agent:claude-opus-4-7",
  "basicPassAt1": 39.08045977011494,
  "datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
  "publicTaskCount": 50,
  "tastefulPassAt1": 13.793103448275861,
  "agentDescription": "Claude Opus 4.7 via mini-swe-agent harness (Portkey→Bedrock)",
  "privateTaskCount": 50,
  "upstreamProvider": "anthropic",
  "upstreamRunCount": 50,
  "averageAgentSteps": 157.95402298850576,
  "averageOutputTokens": 97643.86206896552,
  "averageTotalCostUsd": 8.871201140229886,
  "averageOutputCostUsd": 2.4410965517241383
}

Evidence observed 2026-06-30

13.8 / 100
SWE-rebenchswe_rebench

vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · Claude Opus 4.7-high · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Claude Opus 4.7-high__tools · record Claude Opus 4.7-high__tools:1772323200000:1778803200000

View run source

Source metadata
{
  "passAt5": 66.36363636363637,
  "developer": "anthropic",
  "instanceType": "model",
  "contextPolicy": "128k unless the model supports less",
  "attemptsPerTask": 5,
  "totalTokenUsage": 1526135.3290909089,
  "modelReleaseDate": "2026-04-16",
  "scoreStandardError": 1.4545454545454541,
  "cachedTokenPercentage": 94.18072169671689,
  "modelReleaseTimestamp": 1776297600000,
  "standardContextTokens": 128000,
  "averageInstanceCostUsd": 1.3181382954545455,
  "potentialContamination": true,
  "aggregateTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  },
  "publishedTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  }
}

Evidence observed 2026-05-15

53.1 / 100
Terminal-Bench 2.1terminal_bench

v2.1 · official-leaderboard · Opus 4.7 (max) · harness [email protected] · effort max · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider anthropic/claude-opus-4-7 · record leaderboard/submissions/2026-05-01-anthropic-claude-opus-4-7-max-terminus-2.json · run 10e2e56b-ed31-5f65-a489-69f78b902adf

View run source

Source metadata
{
  "passAt2": 0.7438,
  "passAt3": 0.782,
  "passAt4": 0.809,
  "passAt5": 0.8315,
  "taskCount": 89,
  "actualTokens": {
    "output": 12451178,
    "cachedInput": 336161721,
    "uncachedInput": 16646631
  },
  "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/46",
  "agentDisplayUrl": "https://www.tbench.ai/news/terminus",
  "modelDisplayUrl": "https://www.anthropic.com/news/claude-opus-4-7",
  "actualTrialCount": 445,
  "agentOrganization": "Terminal-Bench",
  "modelOrganization": "Anthropic",
  "actualTotalCostUsd": 582.26,
  "rewardHacksPercent": 0,
  "accuracyStandardError": 1.37,
  "submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-05-01-anthropic-claude-opus-4-7-max-terminus-2.json",
  "disqualifiedTrialCount": 0,
  "expectedAttemptsPerTask": 5,
  "sourceFilterReasoningEffort": "max",
  "actualAverageTrialDurationSeconds": 1042.7
}

Evidence observed 2026-05-01

66.1 / 100
Terminal-Bench 2.1terminal_bench

v2.1 · official-leaderboard · Opus 4.7 (max) · harness [email protected] · effort max · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider anthropic/claude-opus-4-7 · record leaderboard/submissions/2026-05-01-anthropic-claude-opus-4-7-max-claude-code.json · run 10e2e56b-ed31-5f65-a489-69f78b902adf

View run source

Source metadata
{
  "passAt2": 0.7801,
  "passAt3": 0.8124,
  "passAt4": 0.83,
  "passAt5": 0.8408,
  "taskCount": 89,
  "actualTokens": {
    "output": 14896548,
    "cachedInput": 806584422,
    "uncachedInput": 31873388
  },
  "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/44",
  "agentDisplayUrl": "https://claude.com/claude-code",
  "modelDisplayUrl": "https://www.anthropic.com/news/claude-opus-4-7",
  "actualTrialCount": 447,
  "agentOrganization": "Anthropic",
  "modelOrganization": "Anthropic",
  "actualTotalCostUsd": 599.52,
  "rewardHacksPercent": 0.45,
  "accuracyStandardError": 1.41,
  "submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-05-01-anthropic-claude-opus-4-7-max-claude-code.json",
  "disqualifiedTrialCount": 2,
  "expectedAttemptsPerTask": 5,
  "sourceFilterReasoningEffort": "max",
  "actualAverageTrialDurationSeconds": 799.6
}

Evidence observed 2026-05-01

68.9 / 100