Claude Sonnet 4.5: benchmarks, price and rank
Claude Sonnet 4.5 from Anthropic is 81st of 123 rated AI models on Spezia's leaderboard. It costs $3 in, $15 out per million tokens.
- 81st of 123 rated models
- Rating 959
- Rated on 10 benchmarks
- Closed
- Released Sep 29, 2025
- 1 million tokens of context
- Knows the world to January 2025
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 62nd of 66 on FrontierMath Tier 4
- 69th of 76 on FrontierMath
- 14th of 17 on Remote Labor Index
Price: $3 in, $15 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.
- Remote Labor Index2.1%
Real freelance projects that people were paid to do, from design and video to architecture, games and data work. The model gets the same brief and files the freelancer got and has to hand back finished work.
14th of 17. Independent result from Epoch AI.
- Humanity's Last Exam13.7%
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.
- Vending-Bench 2$3,839
The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.
42nd of 60. Independent result from Epoch AI.
- SimpleBench54.3%
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.
51st of 68. Independent result from Epoch AI.
- SimpleQA Verified30.7%
Short factual questions with one checked answer, asked without web search.
63rd of 78. Independent result from Epoch AI.
- FrontierMath23.9%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
69th of 76. Independent result from Epoch AI.
- LMArena text1,439
People put a question to two anonymous models and vote for the better answer.
52nd of 107. Independent result from LMArena.
- LMArena WebDev1,393
People ask two anonymous models to build the same web page or app and vote for the better one.
73rd of 98. Independent result from LMArena.
- SWE-bench Verified71.3%
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 Diamond82.3%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
84th of 103. Independent result from Epoch AI.
5 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.