Claude Opus 4.1: benchmarks, price and rank
Claude Opus 4.1 from Anthropic is 96th of 123 rated AI models on Spezia's leaderboard. It costs $15 in, $75 out per million tokens.
- 96th of 123 rated models
- Rating 853
- Rated on 6 benchmarks
- Closed
- Released Aug 5, 2025
- 200,000 tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 76th of 76 on FrontierMath
- 62nd of 66 on FrontierMath Tier 4
- 92nd of 103 on GPQA Diamond
Price: $15 in, $75 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- Humanity's Last Exam11.5%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
Independent result from Epoch AI.
- SimpleBench60%
Multiple-choice puzzles about everyday situations, space, time and people, written to trip up models that pattern-match instead of think. Ordinary adults do well on them.
43rd of 68. Independent result from Epoch AI.
- FrontierMath12.6%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
76th of 76. Independent result from Epoch AI.
- LMArena text1,419
People put a question to two anonymous models and vote for the better answer.
69th of 107. Independent result from LMArena.
- LMArena WebDev1,389
People ask two anonymous models to build the same web page or app and vote for the better one.
74th of 98. Independent result from LMArena.
- SWE-bench Verified73.3%
Real bug reports and feature requests from popular open-source Python projects. The model has to change the code so the project's hidden tests pass.
Independent result from Epoch AI.
- GPQA Diamond77.3%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
92nd of 103. Independent result from Epoch AI.
- FrontierMath Tier 42.4%
Research-level problems that take professional mathematicians days.
62nd of 66. Independent result from Epoch AI.
- Epoch Capabilities Index144.8
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
79th of 94. Independent result from Epoch AI.
2 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.