Claude Opus 4.6: benchmarks, price and rank
Claude Opus 4.6 from Anthropic is 48th of 123 rated AI models on Spezia's leaderboard, strongest on LMArena text and DeepSearchQA. It costs $5 in, $25 out per million tokens.
- 48th of 123 rated models
- Rating 1,363
- Rated on 16 benchmarks
- Closed
- Released Feb 4, 2026
- 1 million tokens of context
Where it is strongest
- 7th of 107 on LMArena text
- 3rd of 8 on DeepSearchQA
Where it falls behind
- 25th of 33 on MCP Atlas
- 34th of 45 on CharXiv Reasoning
- 39th of 56 on APEX-Agents
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 Index4.2%
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.
11th of 17. Independent result from Epoch AI.
- APEX-Agents46.3%
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.
39th of 56. Independent result from Epoch AI.
- BrowseComp84%
Questions whose answers are hidden deep on the web and take many searches and pages to track down.
16th of 56. The maker's own number, from Anthropic, via LLM Stats.
- MCP Atlas62.7%
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.
25th of 33. The maker's own number, from Anthropic, via LLM Stats.
- Humanity's Last Exam34.4%
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$8,018
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.
17th of 60. Independent result from Epoch AI.
- SimpleBench67.6%
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.
27th of 68. Independent result from Epoch AI.
- SimpleQA Verified47%
Short factual questions with one checked answer, asked without web search.
37th of 78. Independent result from Epoch AI.
- FrontierMath66.0%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
36th of 76. Independent result from Epoch AI.
- MMMU-Pro77.3%
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.
23rd of 51. The maker's own number, from Anthropic, via LLM Stats.
15 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.