Claude Sonnet 5
Made by Anthropic, released 30 Jun 2026. Epoch AI lists its access as “API access”. No Top tier or Strong results yet among the models listed here.
In short
What it does well
No Top tier or Strong ratings on the four main tests yet.
Where it falls short
- Knowledge: Behind the leaders (38th of 43 listed models)
- Writing: Behind the leaders (60th of 77 listed models)
- Coding: Middle (40th of 77 listed models)
- Maths: Middle (26th 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
- Behind the leadersHow often people preferred its answers to writing prompts. 1,416 on Arena's scale · Source for Claude Sonnet 5 writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,484 on Arena's scale · Source for Claude Sonnet 5 coding score (lmarena)
- Maths
- MiddleHow many very hard maths problems it solved. 65.6% · Source for Claude Sonnet 5 maths score (epoch)
- Knowledge
- Behind the leadersHow many short factual questions it answered correctly. 33.7% · Source for Claude Sonnet 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: 33rd of 77 on prompts that need expert knowledge, against 61st of 77 overall. Source for Expert-level prompts
- Long prompts: 36th of 77 on long, detailed prompts, against 61st of 77 overall. Source for Long prompts
- Software and IT: 43rd of 77 on software and IT questions, against 61st of 77 overall. Source for Software and IT
Relatively weaker
No category stands out as clearly weaker than its overall position.
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 33rd of 77 | 1,490 95% range 1,482 to 1,498 | 5,869 | Source for Expert-level prompts |
| Hard prompts Kind of request | 44th of 77 | 1,462 95% range 1,457 to 1,466 | 34,746 | Source for Hard prompts |
| Long prompts Kind of request | 36th of 77 | 1,463 95% range 1,458 to 1,468 | 24,337 | Source for Long prompts |
| Longer conversations Kind of request | 48th of 77 | 1,453 95% range 1,446 to 1,460 | 8,942 | Source for Longer conversations |
| Chinese Language | 59th of 76 | 1,478 95% range 1,468 to 1,488 | 4,099 | Source for Chinese |
| English prompts Language | 59th of 77 | 1,451 95% range 1,446 to 1,456 | 22,133 | Source for English prompts |
| French Language | 48th of 72 | 1,464 95% range 1,448 to 1,479 | 1,783 | Source for French |
| German Language | 46th of 55 | 1,440 95% range 1,419 to 1,461 | 844 | Source for German |
| Japanese Language | 34th of 54 | 1,422 95% range 1,399 to 1,444 | 814 | Source for Japanese |
| Korean Language | 40th of 54 | 1,411 95% range 1,391 to 1,432 | 917 | Source for Korean |
| Non-English prompts Language | 57th of 77 | 1,431 95% range 1,426 to 1,436 | 30,811 | Source for Non-English prompts |
| Russian Language | 45th of 77 | 1,450 95% range 1,441 to 1,458 | 6,149 | Source for Russian |
| Spanish Language | 56th of 70 | 1,441 95% range 1,425 to 1,457 | 1,524 | Source for Spanish |
| Entertainment, sport and media Topic | 59th of 77 | 1,412 95% range 1,405 to 1,418 | 13,672 | Source for Entertainment, sport and media |
| Law and government Topic | 51st of 76 | 1,453 95% range 1,444 to 1,462 | 4,498 | Source for Law and government |
| Medicine and health Topic | 56th of 75 | 1,444 95% range 1,434 to 1,454 | 3,799 | Source for Medicine and health |
| Science Topic | 46th of 77 | 1,462 95% range 1,454 to 1,469 | 8,725 | Source for Science |
| Software and IT Topic | 43rd of 77 | 1,475 95% range 1,469 to 1,480 | 20,391 | 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
- Writing and creating content: rated Behind the leaders on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Coding and building things: rated Middle on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: rated Middle on hard maths problems. Compare it with GPT-6.1 Sol, the best-supported choice for this task.
- Business emails and everyday work: rated Middle on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: rated Behind the leaders 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)
- 30 Jun 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
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) |
1,443 Arena score 95% range 1,439 to 1,447, 52,952 votes |
Behind the leaders | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,416 Arena score 95% range 1,409 to 1,423, 10,993 votes |
Behind the leaders | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,484 Arena score 95% range 1,478 to 1,490, 14,080 votes |
Middle | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,469 Arena score 95% range 1,457 to 1,481, 2,449 votes |
Strong | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,453 Arena score 95% range 1,447 to 1,458, 18,658 votes |
Strong | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,437 Arena score 95% range 1,430 to 1,444, 10,102 votes |
Middle | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Sonnet 5 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,540 Arena score 95% range 1,534 to 1,546, 16,832 votes |
Middle | effort: High, bradley-terry rating | Claude Sonnet 5 (High) lmarena · webdev/latest |
28 Oct 2026 | Source for Claude Sonnet 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 |
65.6% share of problems solved standard error ±2.8 points |
Middle | effort: max, best score across scorers | claude-sonnet-5_max epoch · frontiermath_tiers_1_3_v2.csv |
30 Jun 2026 | Source for Claude Sonnet 5 FrontierMath Tiers 1-3 (v2) score (epoch) · Run details for FrontierMath Tiers 1-3 (v2) |
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
80.0% share of problems solved standard error ±6.0 points |
Behind the leaders | effort: max, best score across scorers | claude-sonnet-5_max epoch · otis_mock_aime_2024_2025.csv |
6 Aug 2026 | Source for Claude Sonnet 5 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
80.3% share of questions correct standard error ±2.8 points |
Behind the leaders | effort: max, best score across scorers | claude-sonnet-5_max epoch · gpqa_diamond.csv |
6 Aug 2026 | Source for Claude Sonnet 5 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
33.7% share of questions correct standard error ±1.5 points |
Behind the leaders | effort: max, best score across scorers | claude-sonnet-5_max epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Claude Sonnet 5 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
42.7% 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_unknown epoch · frontiercode_external.csv |
not provided | Source for Claude Sonnet 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.