Claude Sonnet 5.5
Made by Anthropic, released 28 Sep 2026. Epoch AI lists its access as “API access”. Appears strongest at coding, maths and writing among the models listed here.
In short
What it does well
- Coding: Top tier (10th of 77 listed models)
- Maths: Top tier (7th of 43 listed models)
- Writing: Top tier (14th of 77 listed models)
Where it falls short
- Knowledge: Middle (27th of 43 listed models)
What we don't know yet
- Fixing real software bugs: Not enough data
The four ratings
- Top tier
- Strong
- Middle
- Behind the leaders
- Not enough data
Ratings compare only the 77 models listed here, in quarters, best first. “Not enough data” means no result yet. It is never a low score.
- Writing
- Top tierHow often people preferred its answers to writing prompts. 1,470 on Arena's scale · Source for Claude Sonnet 5.5 writing score (lmarena)
- Coding
- Top tierHow often people preferred its answers to coding questions. 1,512 on Arena's scale · Source for Claude Sonnet 5.5 coding score (lmarena)
- Maths
- Top tierHow many very hard maths problems it solved. 88.8% · Source for Claude Sonnet 5.5 maths score (epoch)
- Knowledge
- MiddleHow many short factual questions it answered correctly. 46.5% · Source for Claude Sonnet 5.5 knowledge score (epoch)
Evidence completeness: Broad evidence, 12 of 13 tests have a result.
Where it is relatively stronger or weaker
This compares each kind of request with the model's own overall position among the 77 listed models, using Arena's votes. It is about performance on different languages, kinds of request and topics, not about political or social bias.
Relatively stronger
- Expert-level prompts: 8th of 77 on prompts that need expert knowledge, against 25th of 77 overall. Source for Expert-level prompts
Relatively weaker
- Spanish: 48th of 70 on questions asked in Spanish, against 25th of 77 overall. Source for Spanish
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 8th of 77 | 1,527 95% range 1,509 to 1,546 | 1,024 | Source for Expert-level prompts |
| Hard prompts Kind of request | 15th of 77 | 1,494 95% range 1,485 to 1,502 | 6,168 | Source for Hard prompts |
| Long prompts Kind of request | 11th of 77 | 1,494 95% range 1,484 to 1,504 | 4,212 | Source for Long prompts |
| Longer conversations Kind of request | 33rd of 77 | 1,468 95% range 1,452 to 1,484 | 1,445 | Source for Longer conversations |
| Chinese Language | 10th of 76 | 1,537 95% range 1,517 to 1,558 | 859 | Source for Chinese |
| English prompts Language | 15th of 77 | 1,484 95% range 1,473 to 1,494 | 3,741 | Source for English prompts |
| French Language | 12th of 72 | 1,498 95% range 1,468 to 1,527 | 407 | Source for French |
| Non-English prompts Language | 30th of 77 | 1,456 95% range 1,448 to 1,464 | 6,288 | Source for Non-English prompts |
| Russian Language | 33rd of 77 | 1,461 95% range 1,444 to 1,477 | 1,400 | Source for Russian |
| Spanish Language | 48th of 70 | 1,447 95% range 1,417 to 1,477 | 359 | Source for Spanish |
| Entertainment, sport and media Topic | 15th of 77 | 1,460 95% range 1,447 to 1,472 | 2,615 | Source for Entertainment, sport and media |
| Law and government Topic | 21st of 76 | 1,485 95% range 1,464 to 1,506 | 822 | Source for Law and government |
| Medicine and health Topic | 25th of 75 | 1,476 95% range 1,453 to 1,499 | 703 | Source for Medicine and health |
| Science Topic | 22nd of 77 | 1,487 95% range 1,472 to 1,502 | 1,704 | Source for Science |
| Software and IT Topic | 13th of 77 | 1,504 95% range 1,494 to 1,515 | 3,416 | Source for Software and IT |
Bias: what we can and can't see
Our sources do not measure political lean, stereotyping, flattery (agreeing with you too readily) or safety behaviour, so we cannot say how any model does on those. What we can show is above: where a model is relatively stronger or weaker across languages, kinds of request and topics. Also, people voting in Arena can favour answer style, such as length and formatting, and our numbers do not adjust for that. See what AI bias means and what these tests can tell you.
Best-supported use cases
This model is not among the options we recommend for any of the five tasks. That reflects the rules and the models listed, not a verdict on the model.
Where an alternative might be more suitable
- Business emails and everyday work: rated Strong on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: rated Middle on short factual questions. Compare it with Gemini 4 Argon, the best-supported choice for this task.
What it is
- Maker
- Anthropic
- Release date (Epoch AI)
- 28 Sep 2026
- Access, as listed by Epoch AI
- API access
- Licence, as listed by Arena
- Proprietary
- Maker's country (Epoch AI)
- United States of America
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
Arena settings 'xHigh'; Epoch runs 'max' (FrontierCode: 'xhigh').
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Proprietary. The model's files are not published, so it is generally available only through its maker or partners the maker chooses.
How you can reach it (an app, a website, a developer API or a third-party tool) and what that costs are not covered by our benchmark data. Where we could verify prices from the maker's own pages, they are shown under Price. Epoch AI lists access as “API access”. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
What Anthropic's own page says about the Sonnet family (USD ($ as shown; the page does not state a currency code); checked 28 Oct 2026)
- Free ($0): Sonnet available
- Pro ($20 per month billed monthly, or $17 per month billed annually ($200 up front)): Sonnet available
- Max (From $100 per month): Sonnet available
The page marks plans against model families, not versions, so it does not say which version of a family a plan includes. Check that before relying on it.
See Claude plans and pricing (checked 28 Oct 2026). Page opened and read.
We never infer subscription prices from API prices. New to “tokens” and “per million”? See how AI pricing works.
Good to remember
- Benchmarks are samples of tasks. None proves performance in every situation.
- Arena scores come from people choosing between answers. That measures preference, not correctness.
- Ratings are relative to the 77 models listed here. A different set would change them.
- Sources test models at different settings. Each result shows the setting used, and we do not adjust it.
The evidence, for the curious
Show all 13 tests with settings and sources
| Test | Result | Rating | Setting used | Source identifier | Observed | Links |
|---|---|---|---|---|---|---|
| Arena text: overall preference Arena 'text' leaderboard (Bradley-Terry rating, no style control) |
1,473 Arena score 95% range 1,466 to 1,480, 10,033 votes |
Strong | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,470 Arena score 95% range 1,457 to 1,484, 2,278 votes |
Top tier | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,512 Arena score 95% range 1,499 to 1,525, 2,339 votes |
Top tier | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,504 Arena score 95% range 1,478 to 1,530, 497 votes |
Top tier | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,492 Arena score 95% range 1,481 to 1,503, 3,357 votes |
Top tier | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,466 Arena score 95% range 1,451 to 1,481, 1,666 votes |
Strong | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,770 Arena score 95% range 1,758 to 1,781, 4,469 votes |
Top tier | effort: xHigh, bradley-terry rating | Claude Sonnet 5.5 (xHigh) lmarena · webdev/latest |
28 Oct 2026 | Source for Claude Sonnet 5.5 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
88.8% share of problems solved standard error ±1.9 points |
Top tier | effort: max, best score across scorers | claude-sonnet-5-5_max epoch · frontiermath_tiers_1_3_v2.csv |
29 Sep 2026 | Source for Claude Sonnet 5.5 FrontierMath Tiers 1-3 (v2) score (epoch) No public run log in the data file. |
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
100.0% share of problems solved standard error ±0.0 points |
Top tier | effort: max, best score across scorers | claude-sonnet-5-5_max epoch · otis_mock_aime_2024_2025.csv |
29 Sep 2026 | Source for Claude Sonnet 5.5 OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
95.6% share of questions correct standard error ±1.4 points |
Top tier | effort: max, best score across scorers | claude-sonnet-5-5_max epoch · gpqa_diamond.csv |
29 Sep 2026 | Source for Claude Sonnet 5.5 GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
46.5% share of questions correct standard error ±1.6 points |
Middle | effort: max, best score across scorers | claude-sonnet-5-5_max epoch · simpleqa_verified.csv |
29 Sep 2026 | Source for Claude Sonnet 5.5 SimpleQA Verified score (epoch) No public run log in the data file. |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
52.1% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: xhigh, tool: claude-code, mean@5 | claude-sonnet-5-5_xhigh epoch · frontiercode_external.csv |
not provided | Source for Claude Sonnet 5.5 FrontierCode (reported by Cognition) score (epoch) · Run details for FrontierCode (reported by Cognition) |
Missing evidence
Not enough data for these tests:
- SWE-bench Verified (Epoch runs)
Missing results are not low scores and do not count against the model.
Where a source gives no public run log, we cannot show the run behind the score. See data sources.
Not sure this is the right one?
Tell us what you need help with and we'll narrow the options down.