Claude Sonnet 5.5: benchmarks, price and rank
Claude Sonnet 5.5 from Anthropic is 7th of 123 rated AI models on Spezia's leaderboard, strongest on Terminal-Bench 4.0 and SWE-Bench Pro. It costs $2 in, $10 out per million tokens.
- 7th of 123 rated models
- Rating 1,887
- First on 1 of 17 benchmarks
- Closed
- Released Sep 28, 2026
- 1 million tokens of context
- Knows the world to June 2026
Where it is strongest
- 1st of 17 on Terminal-Bench 4.0
- 3rd of 50 on SWE-Bench Pro
- 4th of 56 on APEX-Agents
- 2nd of 6 on OSWorld 2.1
- 3rd of 98 on LMArena WebDev
Where it falls behind
- 7th of 13 on OfficeQA Pro
Price: $2 in, $10 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-Agents75.5%
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.
4th of 56. Independent result from Epoch AI.
- Terminal-Bench 4.070.6%
Hard jobs done in a real computer terminal: building and fixing software, setting up systems, and science and engineering problems.
1st of 17. The maker's own number, from Anthropic, via LLM Stats.
- OSWorld 2.143.5%
The newer version of OSWorld, with longer desktop tasks that are graded at several checkpoints along the way.
2nd of 6. The maker's own number, from Anthropic, via LLM Stats.
- SWE-Bench Pro81.3%
Long changes to real codebases in several languages, often across many files, including code from private and copyleft projects that models are unlikely to have seen.
3rd of 50. The maker's own number, from Anthropic, via LLM Stats.
- FrontierSWE61.9%
Open-ended technical projects that take hours to tens of hours, from making systems faster to building large programs and applied machine learning research. Each run gets a 20-hour budget.
4th of 21. Independent result from Epoch AI.
- Humanity's Last Exam46.1%
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$11,165
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.
7th of 60. Independent result from Epoch AI.
- GDPval-AA1,844
Work products from dozens of occupations, the kind of documents, spreadsheets and plans professionals hand in, made by the model and compared head to head with other models' work.
3rd of 5. The maker's own number, from Anthropic, via LLM Stats.
- CursorBench55.5%
Ambiguous coding tasks that span many files, taken from real sessions in the Cursor code editor.
4th of 20. Independent result from Epoch AI.
- DeepSWE 1.171%
Software engineering tasks run in the same simple agent setup for every model.
12th of 27. The maker's own number, from Anthropic, via LLM Stats.
13 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.