Claude Opus 4.6
Made by Anthropic, released 5 Feb 2026. Epoch AI lists its access as “API access”. Appears strongest at coding and writing among the models listed here.
In short
What it does well
- Coding: Top tier (5th of 77 listed models)
- Writing: Top tier (4th of 77 listed models)
Where it falls short
- Knowledge: Middle (25th of 43 listed models)
- Maths: Middle (24th 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. 1,504 on Arena's scale · Source for Claude Opus 4.6 writing score (lmarena)
- Coding
- Top tierHow often people preferred its answers to coding questions. 1,531 on Arena's scale · Source for Claude Opus 4.6 coding score (lmarena)
- Maths
- MiddleHow many very hard maths problems it solved. 66.0% · Source for Claude Opus 4.6 maths score (epoch)
- Knowledge
- MiddleHow many short factual questions it answered correctly. 47.0% · Source for Claude Opus 4.6 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
No category stands out as clearly stronger than its overall position.
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 | 6th of 77 | 1,543 95% range 1,535 to 1,550 | 7,698 | Source for Expert-level prompts |
| Hard prompts Kind of request | 5th of 77 | 1,525 95% range 1,521 to 1,529 | 53,763 | Source for Hard prompts |
| Long prompts Kind of request | 4th of 77 | 1,518 95% range 1,513 to 1,522 | 35,795 | Source for Long prompts |
| Longer conversations Kind of request | 2nd of 77 | 1,512 95% range 1,506 to 1,518 | 14,319 | Source for Longer conversations |
| Chinese Language | 6th of 76 | 1,551 95% range 1,542 to 1,559 | 5,913 | Source for Chinese |
| English prompts Language | 3rd of 77 | 1,512 95% range 1,507 to 1,516 | 37,010 | Source for English prompts |
| French Language | 3rd of 72 | 1,512 95% range 1,499 to 1,525 | 2,770 | Source for French |
| German Language | 6th of 55 | 1,502 95% range 1,485 to 1,519 | 1,336 | Source for German |
| Japanese Language | 12th of 54 | 1,487 95% range 1,467 to 1,508 | 986 | Source for Japanese |
| Korean Language | 13th of 54 | 1,450 95% range 1,433 to 1,467 | 1,417 | Source for Korean |
| Non-English prompts Language | 7th of 77 | 1,488 95% range 1,484 to 1,492 | 47,491 | Source for Non-English prompts |
| Russian Language | 11th of 77 | 1,495 95% range 1,488 to 1,501 | 9,833 | Source for Russian |
| Spanish Language | 3rd of 70 | 1,505 95% range 1,493 to 1,518 | 2,864 | Source for Spanish |
| Entertainment, sport and media Topic | 4th of 77 | 1,492 95% range 1,487 to 1,498 | 19,162 | Source for Entertainment, sport and media |
| Law and government Topic | 5th of 76 | 1,511 95% range 1,503 to 1,519 | 6,874 | Source for Law and government |
| Medicine and health Topic | 8th of 75 | 1,504 95% range 1,496 to 1,512 | 6,343 | Source for Medicine and health |
| Science Topic | 6th of 77 | 1,518 95% range 1,512 to 1,524 | 14,037 | Source for Science |
| Software and IT Topic | 6th of 77 | 1,525 95% range 1,521 to 1,530 | 31,981 | 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
- Homework and maths: rated Middle on hard maths problems. Compare it with GPT-6.1 Sol, 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)
- 5 Feb 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
Epoch lists more than one row for 'claude-opus-4-6' in swe_bench_verified.csv, so that result is not used.
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 Opus family (USD ($ as shown; the page does not state a currency code); checked 28 Oct 2026)
- Free ($0): Opus not available
- Pro ($20 per month billed monthly, or $17 per month billed annually ($200 up front)): Opus available
- Max (From $100 per month): Opus 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) |
1,502 Arena score 95% range 1,498 to 1,505, 84,512 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,504 Arena score 95% range 1,498 to 1,511, 15,580 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,531 Arena score 95% range 1,526 to 1,537, 21,789 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,518 Arena score 95% range 1,508 to 1,527, 4,364 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,521 Arena score 95% range 1,516 to 1,526, 27,276 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,497 Arena score 95% range 1,491 to 1,503, 16,500 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,546 Arena score 95% range 1,541 to 1,552, 19,316 votes |
Strong | effort: High, bradley-terry rating | Claude Opus 4.6 (High) lmarena · webdev/latest |
28 Oct 2026 | Source for Claude Opus 4.6 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
66.0% share of problems solved standard error ±2.8 points |
Middle | effort: max, best score across scorers | claude-opus-4-6_max epoch · frontiermath_tiers_1_3_v2.csv |
11 Jun 2026 | Source for Claude Opus 4.6 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 |
91.1% share of problems solved standard error ±4.3 points |
Middle | effort: max, best score across scorers | claude-opus-4-6_max epoch · otis_mock_aime_2024_2025.csv |
6 Aug 2026 | Source for Claude Opus 4.6 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
88.4% share of questions correct standard error ±2.3 points |
Middle | effort: max, best score across scorers | claude-opus-4-6_max epoch · gpqa_diamond.csv |
6 Aug 2026 | Source for Claude Opus 4.6 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
47.0% share of questions correct standard error ±1.6 points |
Middle | effort: max, best score across scorers | claude-opus-4-6_max epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Claude Opus 4.6 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 |
26.6% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: high, tool: claude-code, mean@5 | claude-opus-4-6_unknown epoch · frontiercode_external.csv |
not provided | Source for Claude Opus 4.6 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.