Claude Opus 4.7

AnthropicReleased 16 Apr 2026ClosedFlagshipDate verified

Compare Announcement

169158–180Index score#21 of 229 models

7/ 8Core tests taken5 of 6 areas · plus 19 anchor tests

−1Versus the frontier at releasebest then: GPT-5.4Replaced by Claude Opus 4.8

$5.0/ $25Price per million tokensinput / output, list price

1MContext windowtokens it reads at once

Where it sitson the frontier

GPT-5.3-Codex reached this score 2 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence

GPQA Diamond

90%

Humanity's Last Exam

36%

Mathsevidence

FrontierMath T1-3

70%

Codingevidence

SWE-bench Verified

83%

Terminal-Bench

80%

Agentsevidence

APEX-Agents

49%

Novel problemsevidence

ARC-AGI-2

76%

Long tasksno evidence yet

METR time horizon

no result

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#21of 219 · 169

Epoch Capabilities Indexoverall capability from many benchmarks#22of 239 · 156.3 LiveBench · Overalloverall, with fresh questions to limit contamination#24of 58 · 76.5

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.