Claude Opus 4

AnthropicReleased 22 May 2025ClosedFlagshipDate verified

Compare Announcement

137126–148Index score#96 of 229 models

5/ 8Core tests taken4 of 6 areas · plus 17 anchor tests

−10Versus the frontier at releasebest then: o3Replaced by Claude Opus 4.1

–Price per million tokensno public API price found

–Context windowtokens it reads at once

Where it sitson the frontier

Gemini 2.5 Pro reached this score 2 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence

GPQA Diamond

76%

Humanity's Last Exam

11%

Mathsevidence

FrontierMath T1-3

no result

Codingevidence

SWE-bench Verified

71%

Terminal-Bench

no result

Agentsevidence

APEX-Agents

no result

Novel problemsevidence

ARC-AGI-2

Long tasksevidence

METR time horizon

1.7 h

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

What others sayrank on each leaderboard

The Model Indexindependent tests, our method#96of 219 · 137

Epoch Capabilities Indexoverall capability from many benchmarks#92of 239 · 142.7

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.