Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Qwen3-235B-A22B
Qwen3-235B-A22B is an open-weight model from Alibaba, released Jul 21, 2025. It ranks #166 of 351 on the LMArena text leaderboard with a rating of 1393. It costs $0.09 per million input tokens and $0.55 per million output tokens, with a 256K-token context window.
- Developer
- Alibaba Qwen
- Released
- Jul 21, 2025
- Context window
- 256K
- Price in / out, per 1M tokens
- $0.09 / $0.55
- Weights
- Open · Apache 2.0
- Inputs
- Text
- Reasoning
- No
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 139.4K
- Hugging Face likes
- 813
The rating LMArena published at each update since May 5, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| LiveCodeBenchCoding | 70.62% | 87 / 143 | $0.22 / $0.88 | |
| MedQAMedicine | 90.62% | 44 / 92 | $0.22 / $0.88 | |
| GPQA DiamondReasoning | 70.20% | 95 / 138 | $0.22 / $0.88 | |
| MMLU-ProReasoning | 81.25% | 84 / 138 | $0.22 / $0.88 | |
| AIMEReasoning | 83.96% | 40 / 96 | $0.22 / $0.88 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1393 | 166 / 351 | 37.5K |
| CodingLMArena | 1398 | 178 / 346 | 6.9K |
| MathLMArena | 1397 | 167 / 339 | 2.4K |
| Creative writingLMArena | 1356 | 161 / 349 | 4.6K |
| Instruction followingLMArena | 1362 | 179 / 351 | 9.2K |
| Hard promptsLMArena | 1393 | 173 / 351 | 16.4K |
| Multi-turnLMArena | 1398 | 155 / 349 | 6.5K |
| Long queriesLMArena | 1389 | 168 / 330 | 7.2K |
| ExpertLMArena | 1369 | 183 / 305 | 1.9K |
| Legal and governmentIndustries | 1394 | 165 / 325 | 2.5K |
| Medicine and healthcareIndustries | 1408 | 152 / 325 | 2.3K |
| Business and financeIndustries | 1392 | 154 / 344 | 6.3K |
| ChineseLanguages | 1424 | 162 / 328 | 2.6K |
| SpanishLanguages | 1403 | 144 / 249 | 763 |
| GermanLanguages | 1387 | 135 / 261 | 762 |
| FrenchLanguages | 1368 | 179 / 252 | 530 |
| JapaneseLanguages | 1372 | 111 / 236 | 887 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Qwen3-235B-A22B (Non-Thinking), Qwen3-235B-A22B).
Compare Qwen3-235B-A22B
Alibaba Qwen
Alibaba Cloud’s Qwen team releases a broad family of open-weight models, from small to frontier scale. Founded 2023 (Qwen), based in Hangzhou. qwenlm.github.io
Questions
Who makes Qwen3-235B-A22B?
Qwen3-235B-A22B is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3-235B-A22B cost?
$0.09 per million input tokens and $0.55 per million output tokens, at its provider’s list price.
What is Qwen3-235B-A22B’s context window?
256K tokens (262,144).
How does Qwen3-235B-A22B rank?
#166 of 351 on LMArena’s text leaderboard, rated 1393 (95% interval 1389–1398) from 37,485 votes, as of Oct 22, 2026.
Is Qwen3-235B-A22B open source?
Qwen3-235B-A22B has open weights under the Apache 2.0 license, downloadable from Hugging Face (Qwen/Qwen3-235B-A22B-Instruct-2507).