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-Thinking
Qwen3-235B-A22B-Thinking is an open-weight model from Alibaba, released Jul 25, 2025. It ranks #133 of 351 on the LMArena text leaderboard with a rating of 1415. It costs $0.45 per million input tokens and $3.50 per million output tokens, with a 125K-token context window.
- Developer
- Alibaba Qwen
- Released
- Jul 25, 2025
- Context window
- 125K
- Price in / out, per 1M tokens
- $0.45 / $3.50
- Weights
- Open · Apache 2.0
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 14.8K
- Hugging Face likes
- 418
The rating LMArena published at each update since Aug 1, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1415 | 133 / 351 | 8.8K |
| CodingLMArena | 1424 | 146 / 346 | 1.6K |
| MathLMArena | 1412 | 141 / 339 | 479 |
| Creative writingLMArena | 1384 | 127 / 349 | 1.1K |
| Instruction followingLMArena | 1386 | 151 / 351 | 2.1K |
| Hard promptsLMArena | 1416 | 139 / 351 | 3.8K |
| Multi-turnLMArena | 1406 | 144 / 349 | 1.4K |
| Long queriesLMArena | 1399 | 151 / 330 | 1.6K |
| ExpertLMArena | 1463 | 67 / 305 | 423 |
| Legal and governmentIndustries | 1415 | 142 / 325 | 532 |
| Medicine and healthcareIndustries | 1456 | 58 / 325 | 509 |
| Business and financeIndustries | 1413 | 118 / 344 | 1.5K |
| ChineseLanguages | 1481 | 75 / 328 | 536 |
| SpanishLanguages | 1389 | 160 / 249 | 185 |
| GermanLanguages | 1408 | 116 / 261 | 211 |
| JapaneseLanguages | 1387 | 94 / 236 | 442 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Qwen3-235B-A22B-Thinking
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-Thinking?
Qwen3-235B-A22B-Thinking is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3-235B-A22B-Thinking cost?
$0.45 per million input tokens and $3.50 per million output tokens, at its provider’s list price.
What is Qwen3-235B-A22B-Thinking’s context window?
125K tokens (128,000).
How does Qwen3-235B-A22B-Thinking rank?
#133 of 351 on LMArena’s text leaderboard, rated 1415 (95% interval 1409–1422) from 8,821 votes, as of Oct 22, 2026.
Is Qwen3-235B-A22B-Thinking open source?
Qwen3-235B-A22B-Thinking has open weights under the Apache 2.0 license, downloadable from Hugging Face (Qwen/Qwen3-235B-A22B-Thinking-2507).