Claude Sonnet 4.6: benchmarks, price and rank
Claude Sonnet 4.6 from Anthropic is 62nd of 123 rated AI models on Spezia's leaderboard. It costs $3 in, $15 out per million tokens.
- 62nd of 123 rated models
- Rating 1,222
- Rated on 11 benchmarks
- Closed
- Released Feb 17, 2026
- 1 million tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 27th of 33 on MCP Atlas
- 43rd of 56 on APEX-Agents
- 53rd of 78 on SimpleQA Verified
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.
- APEX-Agents43%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
43rd of 56. Independent result from Epoch AI.
- BrowseComp74.7%
Questions whose answers are hidden deep on the web and take many searches and pages to track down.
29th of 56. The maker's own number, from Anthropic, via LLM Stats.
- MCP Atlas61.3%
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.
27th of 33. The maker's own number, from Anthropic, via LLM Stats.
- Humanity's Last Exam49%
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.
18th of 74. The maker's own number, from Anthropic, via LLM Stats.
- Vending-Bench 2$7,204
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.
20th of 60. Independent result from Epoch AI.
- DeepSWE 1.130%
Software engineering tasks run in the same simple agent setup for every model.
Independent result from LLM Stats.
- SimpleQA Verified35.5%
Short factual questions with one checked answer, asked without web search.
53rd of 78. Independent result from Epoch AI.
- MMMU-Pro75.6%
College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.
30th of 51. The maker's own number, from Anthropic, via LLM Stats.
- LMArena text1,458
People put a question to two anonymous models and vote for the better answer.
33rd of 107. Independent result from LMArena.
- LMArena WebDev1,522
People ask two anonymous models to build the same web page or app and vote for the better one.
46th of 98. Independent result from LMArena.
7 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.