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-VL-235B-A22B-Instruct
Qwen3-VL-235B-A22B-Instruct is an open-weight model from Alibaba, released Sep 23, 2025. It ranks #115 of 351 on the LMArena text leaderboard with a rating of 1420. It costs $0.21 per million input tokens and $1.90 per million output tokens, with a 256K-token context window.
- Developer
- Alibaba Qwen
- Released
- Sep 23, 2025
- Context window
- 256K
- Price in / out, per 1M tokens
- $0.21 / $1.90
- Weights
- Open · Apache 2.0
- Inputs
- Text, Images
- Reasoning
- No
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 290K
- Hugging Face likes
- 428
The rating LMArena published at each update since Sep 30, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1420 | 115 / 351 | 11.3K |
| CodingLMArena | 1438 | 122 / 346 | 2.3K |
| MathLMArena | 1425 | 113 / 339 | 699 |
| Creative writingLMArena | 1366 | 148 / 349 | 1.4K |
| Instruction followingLMArena | 1407 | 114 / 351 | 2.9K |
| Hard promptsLMArena | 1428 | 115 / 351 | 5.7K |
| Multi-turnLMArena | 1428 | 105 / 349 | 1.9K |
| Long queriesLMArena | 1420 | 111 / 330 | 2.2K |
| ExpertLMArena | 1442 | 94 / 305 | 596 |
| Legal and governmentIndustries | 1439 | 90 / 325 | 736 |
| Medicine and healthcareIndustries | 1431 | 115 / 325 | 627 |
| Business and financeIndustries | 1433 | 72 / 344 | 2.2K |
| ChineseLanguages | 1462 | 106 / 328 | 715 |
| SpanishLanguages | 1428 | 103 / 249 | 460 |
| GermanLanguages | 1424 | 92 / 261 | 279 |
| FrenchLanguages | 1452 | 81 / 252 | 262 |
| JapaneseLanguages | 1385 | 95 / 236 | 170 |
| VisionLMArena | 1247 | 67 / 146 | 12.7K |
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-VL-235B-A22B-Instruct
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-VL-235B-A22B-Instruct?
Qwen3-VL-235B-A22B-Instruct is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3-VL-235B-A22B-Instruct cost?
$0.21 per million input tokens and $1.90 per million output tokens, at its provider’s list price.
What is Qwen3-VL-235B-A22B-Instruct’s context window?
256K tokens (262,144).
How does Qwen3-VL-235B-A22B-Instruct rank?
#115 of 351 on LMArena’s text leaderboard, rated 1420 (95% interval 1414–1427) from 11,312 votes, as of Oct 22, 2026.
Is Qwen3-VL-235B-A22B-Instruct open source?
Qwen3-VL-235B-A22B-Instruct has open weights under the Apache 2.0 license, downloadable from Hugging Face (Qwen/Qwen3-VL-235B-A22B-Instruct).