Claude Opus 4.7
Made by Anthropic, released 16 Apr 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 (7th of 77 listed models)
- Writing: Top tier (10th of 77 listed models)
- Knowledge: Strong (21st of 43 listed models)
- Maths: Strong (21st of 43 listed models)
Where it falls short
The four main ratings show no weakness. That is not evidence it has none.
What we don't know yet
Every test we use has a result.
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. 1,486 on Arena's scale · Source for Claude Opus 4.7 writing score (lmarena)
- Coding
- Top tierHow often people preferred its answers to coding questions. 1,519 on Arena's scale · Source for Claude Opus 4.7 coding score (lmarena)
- Maths
- StrongHow many very hard maths problems it solved. 70.2% · Source for Claude Opus 4.7 maths score (epoch)
- Knowledge
- StrongHow many short factual questions it answered correctly. 51.7% · Source for Claude Opus 4.7 knowledge score (epoch)
Evidence completeness: Broad evidence, 13 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 | 11th of 77 | 1,519 95% range 1,511 to 1,527 | 6,918 | Source for Expert-level prompts |
| Hard prompts Kind of request | 10th of 77 | 1,506 95% range 1,501 to 1,510 | 43,653 | Source for Hard prompts |
| Long prompts Kind of request | 8th of 77 | 1,505 95% range 1,500 to 1,510 | 30,080 | Source for Long prompts |
| Longer conversations Kind of request | 3rd of 77 | 1,505 95% range 1,498 to 1,512 | 11,414 | Source for Longer conversations |
| Chinese Language | 13th of 76 | 1,531 95% range 1,521 to 1,541 | 4,172 | Source for Chinese |
| English prompts Language | 10th of 77 | 1,496 95% range 1,491 to 1,501 | 30,177 | Source for English prompts |
| French Language | 9th of 72 | 1,503 95% range 1,489 to 1,517 | 2,292 | Source for French |
| German Language | 8th of 55 | 1,497 95% range 1,478 to 1,515 | 1,022 | Source for German |
| Japanese Language | 15th of 54 | 1,473 95% range 1,449 to 1,497 | 720 | Source for Japanese |
| Korean Language | 12th of 54 | 1,451 95% range 1,432 to 1,470 | 1,110 | Source for Korean |
| Non-English prompts Language | 11th of 77 | 1,480 95% range 1,476 to 1,485 | 34,931 | Source for Non-English prompts |
| Russian Language | 13th of 77 | 1,494 95% range 1,486 to 1,502 | 6,860 | Source for Russian |
| Spanish Language | 6th of 70 | 1,494 95% range 1,480 to 1,509 | 2,049 | Source for Spanish |
| Entertainment, sport and media Topic | 10th of 77 | 1,474 95% range 1,467 to 1,480 | 15,117 | Source for Entertainment, sport and media |
| Law and government Topic | 8th of 76 | 1,504 95% range 1,495 to 1,513 | 5,251 | Source for Law and government |
| Medicine and health Topic | 11th of 75 | 1,495 95% range 1,486 to 1,505 | 4,955 | Source for Medicine and health |
| Science Topic | 11th of 77 | 1,508 95% range 1,501 to 1,514 | 11,046 | Source for Science |
| Software and IT Topic | 7th of 77 | 1,516 95% range 1,511 to 1,521 | 26,193 | 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 Strong on hard maths problems. Compare it with GPT-6.1 Sol, the best-supported choice for this task.
- Research and checking facts: rated Strong 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)
- 16 Apr 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 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) |
1,490 Arena score 95% range 1,486 to 1,493, 65,110 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,486 Arena score 95% range 1,479 to 1,493, 11,769 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,519 Arena score 95% range 1,513 to 1,525, 18,587 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,499 Arena score 95% range 1,488 to 1,509, 3,286 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,498 Arena score 95% range 1,492 to 1,503, 22,726 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,490 Arena score 95% range 1,484 to 1,497, 13,043 votes |
Top tier | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · text/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,558 Arena score 95% range 1,552 to 1,563, 17,859 votes |
Strong | effort: High, bradley-terry rating | Claude Opus 4.7 (High) lmarena · webdev/latest |
28 Oct 2026 | Source for Claude Opus 4.7 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
70.2% share of problems solved standard error ±2.7 points |
Strong | effort: max, best score across scorers | claude-opus-4-7_max epoch · frontiermath_tiers_1_3_v2.csv |
10 Jun 2026 | Source for Claude Opus 4.7 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 |
86.7% share of problems solved standard error ±5.1 points |
Behind the leaders | effort: max, best score across scorers | claude-opus-4-7_max epoch · otis_mock_aime_2024_2025.csv |
6 Aug 2026 | Source for Claude Opus 4.7 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
86.4% share of questions correct standard error ±2.4 points |
Behind the leaders | effort: max, best score across scorers | claude-opus-4-7_max epoch · gpqa_diamond.csv |
6 Aug 2026 | Source for Claude Opus 4.7 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
51.7% share of questions correct standard error ±1.6 points |
Strong | effort: xhigh, best score across scorers | claude-opus-4-7_xhigh epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Claude Opus 4.7 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) SWE-bench Verified, benchmark released 2024-08-13, as run by Epoch AI |
83.5% share of issues resolved standard error ±1.7 points |
Top tier | effort: max, best score across scorers | claude-opus-4-7_max epoch · swe_bench_verified.csv |
20 Apr 2026 | Source for Claude Opus 4.7 SWE-bench Verified (Epoch runs) score (epoch) · Run details for SWE-bench Verified (Epoch runs) |
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
38.5% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: max, tool: claude-code, mean@5 | claude-opus-4-7_unknown epoch · frontiercode_external.csv |
not provided | Source for Claude Opus 4.7 FrontierCode (reported by Cognition) score (epoch) · Run details for FrontierCode (reported by Cognition) |
Missing evidence
Every test we use has a result for this 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.