supermarket

Vision-language

Claude Opus 4.1

By Anthropic, in the Claude Opus family.

Released
5 Aug 2025
Status
Retired
Retired
5 Aug 2026
Context
200K
Max output
32K
Input per 1M tokens
$15.00
Output per 1M tokens
$75.00
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
Jan 2025
Reasoning
Yes
Modalities
text, image → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning26.4664 of 4
Agentic tool use48.3Not ranked1 of 2
Vision & multimodal understanding2.5Not ranked1 of 3
Human preference52.7Not ranked2 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Chess PuzzlesPuzzles solved7.0%Independent—20 Jul 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)80.0%Third partyunknown—https://conceptualreasoning.ai/dtbench via Epoch AI
Earthborne Rangers (EBR-bench)Objectives reached7.9%Independent—25 Jun 2026Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.3708Third partyunknown—https://conceptualreasoning.ai/lmca via Epoch AI
Mystery Game PuzzlesPuzzles solved21.0%Independent24K25 Jul 2026Epoch AI
SimpleBenchScore (AVG@5)60.0%Third party——SimpleBench Leaderboard via Epoch AI
SimpleBenchScore (AVG@5)60.0%Third partyunknown—SimpleBench Leaderboard via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy77.3%Independent16K5 Aug 2025Epoch AI
GPQA DiamondAccuracy76.8%Independent27K5 Aug 2025Epoch AI
GPQA DiamondAccuracy73.2%Independent—5 Aug 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
FrontierMath Tier 4Accuracy2.4%Independent32K11 Jun 2026Epoch AI
FrontierMath Tier 4 (v1)Accuracy4.2%Independent27K5 Aug 2025Epoch AI
FrontierMath Tiers 1-3Accuracy12.6%Independent32K11 Jun 2026Epoch AI
FrontierMath Tiers 1-3 (v1)Accuracy7.2%Independent27K5 Aug 2025Epoch AI
FrontierMath Tiers 1-3 (v1)Accuracy5.9%Independent—5 Aug 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy68.9%Independent27K5 Aug 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy64.4%Independent16K5 Aug 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy40.0%Independent—5 Aug 2025Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
CybenchUnguided challenges solved42.0%Third party——Cybench leaderboard via Epoch AI
METR Time HorizonsAverage task success (Epoch's column)66.8%Third party16K—METR - Measuring AI Ability to Complete Long Tasks via Epoch AI
METR Time HorizonsAverage task success (Epoch's column)61.6%Source not stated——Epoch AI via Epoch AI
SWE-bench Verified% resolved73.3%Independent—11 Feb 2026Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)38.0%Third party——Terminal-Bench v2 Leaderboard via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)38.0%Third partyunknown—https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)36.9%Third party——Terminal-Bench v2 Leaderboard via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)36.9%Third partyunknown—https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)35.1%Third party——Terminal-Bench v2 Leaderboard via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)35.1%Third partyunknown—https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)34.8%Third partyunknown—https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI
Terminal-Bench 2.0Accuracy (mean over trials)34.8%Third party——Terminal-Bench v2 Leaderboard via Epoch AI
WeirdML (v2)Average accuracy45.9%Third party16K—https://htihle.github.io/weirdml.html via Epoch AI

Agentic tool use

Agentic tool use results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Deep Research Bench (FutureSearch)Average score48.3%Third party——https://evals.futuresearch.ai/#drb via Epoch AI

Professional knowledge work

Professional knowledge work results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GDPvalWins vs experts43.6%Source not stated——Epoch AI via Epoch AI

Vision & multimodal understanding

Vision & multimodal understanding results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Visual Physics Comprehension Test (VPCT)Correct35.0%Third party——VPCT leaderboard via Epoch AI
Visual Physics Comprehension Test (VPCT)Correct33.0%Third party16K—VPCT leaderboard via Epoch AI

Writing

Writing results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
LLM Creative Story-Writing Benchmark V1 (Lech Mazur)Mean rubric score (percent of the 10-point scale)84.7%Third party——lechmazur/writing Github repository via Epoch AI
LLM Creative Story-Writing Benchmark V1 (Lech Mazur)Mean rubric score (percent of the 10-point scale)84.5%Third party16K—lechmazur/writing Github repository via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Code Arena: WebDev (arena.ai)Arena score (Elo scale)1390Independent—25 Sep 2026Arena
Code Arena: WebDev (arena.ai)Votes6933Independent—25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1448Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes76940Independent—25 Sep 2026Arena

Other Claude Opus versions

Sources