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
Qwen3.7-Max-Preview
Qwen3.7-Max-Preview is a proprietary model from Alibaba, released May 21, 2026. It ranks #24 of 351 on the LMArena text leaderboard with a rating of 1475. It costs $1.48 per million input tokens and $4.42 per million output tokens, with a 1M-token context window.
- Developer
- Alibaba Qwen
- Released
- May 21, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $1.48 / $4.42
- Weights
- Proprietary
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since May 18, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 68.80% | 66 / 85 | $3.23 | |
| Vibe Code BenchCoding | 47.67% | 63 / 115 | $11.40 | |
| LiveCodeBenchCoding | 87.06% | 19 / 143 | $2.5 / $7.5 | |
| Tax Agent BenchFinance | 15.83% | 54 / 76 | $0.44 | |
| Legal Research BenchLaw | 25.48% | 59 / 85 | $1.40 | |
| MedCodeMedicine | 38.75% | 70 / 107 | $2.5 / $7.5 | |
| GPQA DiamondReasoning | 90.15% | 25 / 138 | $2.5 / $7.5 | |
| MMLU-ProReasoning | 89.31% | 12 / 138 | $2.5 / $7.5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1475 | 24 / 351 | 3.9K |
| CodingLMArena | 1497 | 29 / 346 | 1.2K |
| MathLMArena | 1488 | 23 / 339 | 233 |
| Creative writingLMArena | 1448 | 35 / 349 | 511 |
| Instruction followingLMArena | 1460 | 40 / 351 | 1.4K |
| Hard promptsLMArena | 1482 | 35 / 351 | 2.7K |
| Multi-turnLMArena | 1480 | 24 / 349 | 700 |
| Long queriesLMArena | 1482 | 26 / 330 | 1.7K |
| ExpertLMArena | 1488 | 41 / 305 | 392 |
| Legal and governmentIndustries | 1477 | 33 / 325 | 311 |
| Medicine and healthcareIndustries | 1479 | 28 / 325 | 325 |
| Business and financeIndustries | 1446 | 49 / 344 | 882 |
| ChineseLanguages | 1527 | 25 / 328 | 324 |
| WebDevLMArena | 1515 | 58 / 124 | 8.9K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Qwen3.7-Max-Preview, Qwen3.7-Max (20260517)).
Compare Qwen3.7-Max-Preview
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 Qwen3.7-Max-Preview?
Qwen3.7-Max-Preview is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3.7-Max-Preview cost?
$1.48 per million input tokens and $4.42 per million output tokens, at its provider’s list price.
What is Qwen3.7-Max-Preview’s context window?
1M tokens (1,000,000).
How does Qwen3.7-Max-Preview rank?
#24 of 351 on LMArena’s text leaderboard, rated 1475 (95% interval 1465–1485) from 3,941 votes, as of Oct 22, 2026.
Is Qwen3.7-Max-Preview open source?
No. Qwen3.7-Max-Preview is proprietary and served through its provider’s API.