Claude Opus 4.5: benchmarks, price and rank
Claude Opus 4.5 from Anthropic is 67th of 123 rated AI models on Spezia's leaderboard. It costs $5 in, $25 out per million tokens.
- 67th of 123 rated models
- Rating 1,171
- Rated on 11 benchmarks
- Closed
- Released Nov 24, 2025
- 200,000 tokens of context
- Knows the world to March 2025
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 61st of 66 on FrontierMath Tier 4
- 63rd of 76 on FrontierMath
- 26th of 33 on MCP Atlas
Price: $5 in, $25 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 Index3.8%
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.
12th of 17. Independent result from Epoch AI.
- MCP Atlas62.3%
Multi-step tasks where the model has to pick and combine many real tools, connected through MCP, the standard way agents plug into apps and data.
26th of 33. The maker's own number, from Anthropic, via LLM Stats.
- Humanity's Last Exam25.2%
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$4,967
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.
36th of 60. Independent result from Epoch AI.
- SimpleBench62%
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.
34th of 68. Independent result from Epoch AI.
- SimpleQA Verified45.7%
Short factual questions with one checked answer, asked without web search.
40th of 78. Independent result from Epoch AI.
- FrontierMath34.4%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
63rd of 76. Independent result from Epoch AI.
- LMArena text1,451
People put a question to two anonymous models and vote for the better answer.
38th of 107. Independent result from LMArena.
- LMArena WebDev1,493
People ask two anonymous models to build the same web page or app and vote for the better one.
54th of 98. Independent result from LMArena.
- SWE-bench Verified76.7%
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.
6 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.