Qwen3.5-397B-A17B
Made by Alibaba, released 13 Feb 2026. Epoch AI lists its access as “Open weights (unrestricted)”. 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
- Maths: Behind the leaders (40th of 43 listed models)
- Writing: Behind the leaders (65th of 77 listed models)
- Coding: Middle (57th of 77 listed models)
What we don't know yet
- Short factual questions: Not enough data
- Fixing real software bugs: Not enough data
- Difficult coding tasks: 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. 1,402 on Arena's scale · Source for Qwen3.5-397B-A17B writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,464 on Arena's scale · Source for Qwen3.5-397B-A17B coding score (lmarena)
- Maths
- Behind the leadersHow many very hard maths problems it solved. 31.2% · Source for Qwen3.5-397B-A17B maths score (epoch)
- Knowledge
- Not enough dataNo result yet for short factual questions.
Evidence completeness: Broad evidence, 10 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
- Chinese: 42nd of 76 on questions asked in Chinese, against 63rd of 77 overall. Source for Chinese
- Japanese: 32nd of 54 on questions asked in Japanese, against 63rd of 77 overall. Source for Japanese
- Medicine and health: 46th of 75 on medicine and health questions, against 63rd of 77 overall. Source for Medicine and health
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 | 55th of 77 | 1,461 95% range 1,455 to 1,468 | 10,502 | Source for Expert-level prompts |
| Hard prompts Kind of request | 63rd of 77 | 1,448 95% range 1,444 to 1,451 | 64,295 | Source for Hard prompts |
| Long prompts Kind of request | 58th of 77 | 1,441 95% range 1,437 to 1,445 | 42,999 | Source for Long prompts |
| Longer conversations Kind of request | 55th of 77 | 1,446 95% range 1,441 to 1,452 | 15,723 | Source for Longer conversations |
| Chinese Language | 42nd of 76 | 1,498 95% range 1,490 to 1,506 | 6,888 | Source for Chinese |
| English prompts Language | 65th of 77 | 1,443 95% range 1,439 to 1,447 | 42,806 | Source for English prompts |
| French Language | 50th of 72 | 1,463 95% range 1,450 to 1,475 | 3,179 | Source for French |
| German Language | 42nd of 55 | 1,444 95% range 1,428 to 1,460 | 1,516 | Source for German |
| Japanese Language | 32nd of 54 | 1,428 95% range 1,409 to 1,446 | 1,227 | Source for Japanese |
| Korean Language | 49th of 54 | 1,387 95% range 1,371 to 1,403 | 1,641 | Source for Korean |
| Non-English prompts Language | 62nd of 77 | 1,430 95% range 1,426 to 1,433 | 54,862 | Source for Non-English prompts |
| Russian Language | 62nd of 77 | 1,431 95% range 1,424 to 1,437 | 11,258 | Source for Russian |
| Spanish Language | 55th of 70 | 1,441 95% range 1,429 to 1,452 | 3,107 | Source for Spanish |
| Entertainment, sport and media Topic | 67th of 77 | 1,399 95% range 1,394 to 1,404 | 22,213 | Source for Entertainment, sport and media |
| Law and government Topic | 60th of 76 | 1,442 95% range 1,434 to 1,449 | 7,506 | Source for Law and government |
| Medicine and health Topic | 46th of 75 | 1,455 95% range 1,448 to 1,463 | 7,261 | Source for Medicine and health |
| Science Topic | 53rd of 77 | 1,457 95% range 1,452 to 1,463 | 15,975 | Source for Science |
| Software and IT Topic | 56th of 77 | 1,462 95% range 1,458 to 1,467 | 38,862 | 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
- Research and checking facts: not ranked, because there is not enough data for the main test.
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 Behind the leaders 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: no result on short factual questions, so we cannot say. See which models the evidence does support.
What it is
- Maker
- Alibaba
- Release date (Epoch AI)
- 13 Feb 2026
- Access, as listed by Epoch AI
- Open weights (unrestricted)
- Licence, as listed by Arena
- Apache 2.0
- Maker's country (Epoch AI)
- China
- 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
Open weights. Arena lists its licence as Apache 2.0. In plain terms, the model's files are published under a licence that lets others run it, so it can be offered by more than one company, sometimes at lower cost. That does not guarantee that any particular app is free. Open licences differ, and some restrict commercial use, so check the licence terms before building a business on it.
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 “Open weights (unrestricted)”. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
We have not been able to check this maker's own pricing page, so we show nothing for it.
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) |
1,438 Arena score 95% range 1,435 to 1,441, 97,675 votes |
Behind the leaders | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,402 Arena score 95% range 1,397 to 1,408, 17,395 votes |
Behind the leaders | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,464 Arena score 95% range 1,459 to 1,469, 27,540 votes |
Middle | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,454 Arena score 95% range 1,445 to 1,462, 5,402 votes |
Middle | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,423 Arena score 95% range 1,419 to 1,428, 33,498 votes |
Behind the leaders | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,435 Arena score 95% range 1,429 to 1,440, 19,379 votes |
Middle | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · text/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,400 Arena score 95% range 1,395 to 1,405, 21,096 votes |
Behind the leaders | effort: not stated, bradley-terry rating | Qwen3.5-397B-A17B lmarena · webdev/latest |
28 Oct 2026 | Source for Qwen3.5-397B-A17B Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
31.2% share of problems solved standard error ±2.7 points |
Behind the leaders | effort: none, best score across scorers | qwen3.5-397b-a17b_none epoch · frontiermath_tiers_1_3_v2.csv |
30 Aug 2026 | Source for Qwen3.5-397B-A17B 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 |
82.2% share of problems solved standard error ±5.8 points |
Behind the leaders | effort: none, best score across scorers | qwen3.5-397b-a17b_none epoch · otis_mock_aime_2024_2025.csv |
7 Aug 2026 | Source for Qwen3.5-397B-A17B 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: none, best score across scorers | qwen3.5-397b-a17b_none epoch · gpqa_diamond.csv |
7 Aug 2026 | Source for Qwen3.5-397B-A17B GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified | Not enough data | |||||
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- SimpleQA Verified
- SWE-bench Verified (Epoch runs)
- FrontierCode (reported by Cognition)
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.