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
Qwen3.6-Plus
Qwen3.6-Plus is a proprietary model from Alibaba, released Apr 2, 2026. It ranks #83 of 351 on the LMArena text leaderboard with a rating of 1436. It costs $0.33 per million input tokens and $1.95 per million output tokens, with a 1M-token context window.
- Developer
- Alibaba Qwen
- Released
- Apr 2, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.33 / $1.95
- Weights
- Proprietary
- Inputs
- Text, Images, Video
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Apr 20, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 73.40% | 49 / 85 | $0.87 | |
| Vibe Code BenchCoding | 25.57% | 76 / 115 | $5.45 | |
| LiveCodeBenchCoding | 85.95% | 25 / 143 | $0.5 / $3 | |
| Tax Agent BenchFinance | 7.68% | 66 / 76 | $0.30 | |
| Legal Research BenchLaw | 14.90% | 71 / 85 | $0.70 | |
| MedCodeMedicine | 36.89% | 77 / 107 | $0.5 / $3 | |
| GPQA DiamondReasoning | 87.37% | 39 / 138 | $0.5 / $3 | |
| MMLU-ProReasoning | 87.67% | 24 / 138 | $0.5 / $3 | |
| AIMEReasoning | 94.58% | 13 / 96 | $0.5 / $3 | |
| MMMUReasoning | 84.16% | 27 / 93 | $0.5 / $3 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1436 | 83 / 351 | 48.1K |
| CodingLMArena | 1467 | 74 / 346 | 14.7K |
| MathLMArena | 1450 | 71 / 339 | 2.7K |
| Creative writingLMArena | 1404 | 88 / 349 | 7.2K |
| Instruction followingLMArena | 1424 | 81 / 351 | 16.5K |
| Hard promptsLMArena | 1449 | 76 / 351 | 32.6K |
| Multi-turnLMArena | 1438 | 90 / 349 | 8.4K |
| Long queriesLMArena | 1439 | 78 / 330 | 21.2K |
| ExpertLMArena | 1454 | 77 / 305 | 4.9K |
| Legal and governmentIndustries | 1437 | 95 / 325 | 3.6K |
| Medicine and healthcareIndustries | 1442 | 93 / 325 | 3.5K |
| Business and financeIndustries | 1430 | 79 / 344 | 10.1K |
| ChineseLanguages | 1477 | 81 / 328 | 2.7K |
| SpanishLanguages | 1432 | 99 / 249 | 1.6K |
| GermanLanguages | 1452 | 51 / 261 | 794 |
| FrenchLanguages | 1454 | 78 / 252 | 1.8K |
| JapaneseLanguages | 1390 | 90 / 236 | 554 |
| WebDevLMArena | 1462 | 75 / 124 | 18.6K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Qwen3.6-Plus
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 Qwen3.6-Plus?
Qwen3.6-Plus is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3.6-Plus cost?
$0.33 per million input tokens and $1.95 per million output tokens, at its provider’s list price.
What is Qwen3.6-Plus’s context window?
1M tokens (1,000,000).
How does Qwen3.6-Plus rank?
#83 of 351 on LMArena’s text leaderboard, rated 1436 (95% interval 1432–1441) from 48,142 votes, as of Oct 22, 2026.
Is Qwen3.6-Plus open source?
No. Qwen3.6-Plus is proprietary and served through its provider’s API.