Alibaba (Qwen), open weights
Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B by Alibaba (Qwen) ranks 95th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.2. Its strongest category is multimodal, where it ranks 55th. API pricing starts at $0.70 per million input tokens and $2.80 per million output tokens, with a 131K-token context window.
Last verified
Specifications
- Noometry rank
- #95 of 354
- Index score
- 43.2
- Evidence
- Confirmed 18 results
- Provider
Alibaba (Qwen)
- Released
- April 1, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 131K
- Max output
- 33K
- Input price
- $0.70 / M
- Output price
- $2.80 / M
- Blended price
- $1.22 / M
- Output speed
- Not measured
- Value
- #127 of 219
- Knowledge cutoff
- April 2025
- Input
- text, image
- Hugging Face
- Qwen/Qwen3-VL-235B-A22B-Instruct
Category scores
Each category score combines every public result we have in that category.
- Coding 42.4
- Reasoning 29.3
- Math 39.0
- Knowledge 40.3
- Multimodal 39.8
- Multilingual 51.9
- Instruction Following 74.2
- Long Context 43.4
- Writing & Preference 60.2
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 42.4 | #100 | 1 |
| Reasoning | 29.3 | #92 | 1 |
| Math | 39.0 | #118 | 1 |
| Knowledge | 40.3 | #121 | 1 |
| Multimodal | 39.8 | #55 | 1 |
| Multilingual | 51.9 | #97 | 1 |
| Instruction Following | 74.2 | #101 | 1 |
| Long Context | 43.4 | #98 | 1 |
| Writing & Preference | 60.2 | #99 | 3 |
Strengths and weaknesses
Categories where Qwen3-VL 235B-A22B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 29.3 | +5.7 | #92 of 350, top 27% |
| Coding | 42.4 | +3.7 | #100 of 340, top 30% |
| Writing & Preference | 60.2 | +6.5 | #99 of 312, top 32% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 39.8 | +1.2 | #55 of 128, top 43% |
| Knowledge | 40.3 | +3.0 | #121 of 314, top 39% |
| Math | 39.0 | +2.4 | #118 of 327, top 37% |
Closest competitors
The models ranked just above and below Qwen3-VL 235B-A22B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Qwen3 235B-A22B | #91 | 43.5 | $1.22 | 85 | Compare |
| Gemma 4 26B A4B IT | #92 | 43.5 | $0.11 | — | Compare |
| MiMo-V2.5 | #93 | 43.4 | $0.18 | — | Compare |
| Kimi K2.7 Code | #94 | 43.3 | $1.71 | — | Compare |
| Seed 2.0 Pro | #96 | 43.2 | $1.13 | — | Compare |
| DeepSeek-V3.1-Terminus | #97 | 43.1 | $0.45 | 30 | Compare |
| Hunyuan Vision 1.5 | #98 | 43.1 | — | — | Compare |
| Mistral Large 4 | #99 | 43.1 | $1.03 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1439 | #99 of 294, top 34% | LMArena | 2026-10-08 | |
| LMArena Coding | 1425 | thinking | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1428 | #91 of 297, top 31% | LMArena | 2026-10-08 | |
| LMArena Hard Prompts | 1407 | thinking | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1426 | #94 of 285, top 33% | LMArena | 2026-10-08 | |
| LMArena Math | 1412 | thinking | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1442 | #80 of 273, top 30% | LMArena | 2026-10-08 | |
| LMArena Expert | 1430 | thinking | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1247 | #58 of 122, top 48% | LMArena | 2026-10-09 | |
| LMArena Vision | 1207 | thinking | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1405 | #96 of 297, top 33% | LMArena | 2026-10-08 | |
| LMArena Non-English | 1377 | thinking | LMArena | 2026-10-08 | |
| LMArena Chinese | 1463 | #86 of 285, top 31% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1441 | thinking | LMArena | 2026-10-08 | |
| LMArena French | 1452 | #67 of 223, top 31% | LMArena | 2026-10-08 | |
| LMArena German | 1424 | #73 of 231, top 32% | LMArena | 2026-10-08 | |
| LMArena German | 1415 | thinking | LMArena | 2026-10-08 | |
| LMArena Japanese | 1385 | #73 of 211, top 35% | LMArena | 2026-10-08 | |
| LMArena Korean | 1394 | #62 of 213, top 30% | LMArena | 2026-10-08 | |
| LMArena Korean | 1358 | thinking | LMArena | 2026-10-08 | |
| LMArena Russian | 1408 | #97 of 283, top 35% | LMArena | 2026-10-08 | |
| LMArena Russian | 1369 | thinking | LMArena | 2026-10-08 | |
| LMArena Spanish | 1428 | #86 of 226, top 39% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1403 | thinking | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1406 | #93 of 298, top 32% | LMArena | 2026-10-08 | |
| LMArena Instruction Following | 1374 | thinking | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1420 | #92 of 291, top 32% | LMArena | 2026-10-08 | |
| LMArena Longer Query | 1390 | thinking | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1420 | #91 of 297, top 31% | LMArena | 2026-10-08 | |
| LMArena Text | 1400 | thinking | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1366 | #114 of 295, top 39% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1344 | thinking | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1428 | #85 of 295, top 29% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1387 | thinking | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $0.70 | $2.80 | — | 2026-10-10 |
| bedrock | $0.53 | $2.66 | — | 2026-10-10 |
| deepinfra | $0.20 | $0.88 | $0.11 | 2026-10-10 |
| openrouter | $0.21 | $1.90 | $0.10 | 2026-10-10 |
Compare Qwen3-VL 235B-A22B
- Qwen3-VL 235B-A22B vs Kimi K2.7 Code
- Qwen3-VL 235B-A22B vs Seed 2.0 Pro
- Qwen3-VL 235B-A22B vs MiMo-V2.5
- Qwen3-VL 235B-A22B vs DeepSeek-V3.1-Terminus
- Qwen3-VL 235B-A22B vs Gemma 4 26B A4B IT
- Qwen3-VL 235B-A22B vs Hunyuan Vision 1.5
- Qwen3-VL 235B-A22B vs GPT-6 Astra
- Qwen3-VL 235B-A22B vs Claude Fable 5.1
- Qwen3-VL 235B-A22B vs Gemini 3.8 Flash
- Qwen3-VL 235B-A22B vs Kimi K3
- Qwen3-VL 235B-A22B vs Grok 4.6
- Qwen3-VL 235B-A22B vs GLM-5.3
- Qwen3-VL 235B-A22B vs Muse Spark 1.3
- Qwen3-VL 235B-A22B vs DeepSeek V4 Pro
Other Alibaba (Qwen) models
- Qwen3.8 Max56.8
- Qwen3.7 Max51.5
- Qwen3.6 Max Preview51.5
- Qwen3.6 Plus47.5
- Qwen3.5 397B-A17B46.0
- Qwen3.8 27B46.0
- Qwen3.5 Max Preview45.3
- Qwen3.7 Plus45.3
Frequently asked questions
How good is Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B by Alibaba (Qwen) ranks 95th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.2. Its strongest category is multimodal, where it ranks 55th. API pricing starts at $0.70 per million input tokens and $2.80 per million output tokens, with a 131K-token context window.
How much does Qwen3-VL 235B-A22B cost?
Qwen3-VL 235B-A22B costs $0.70 per million input tokens and $2.80 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen3-VL 235B-A22B's context window?
Qwen3-VL 235B-A22B accepts up to 131K tokens of input and can write up to 33K tokens in one response.
Is Qwen3-VL 235B-A22B open source?
Yes. Qwen3-VL 235B-A22B's weights are downloadable from Hugging Face (Qwen/Qwen3-VL-235B-A22B-Instruct); check the license for commercial terms.
What are Qwen3-VL 235B-A22B's strengths and weaknesses?
Relative to other ranked models, Qwen3-VL 235B-A22B places best in reasoning, coding, writing & preference and lowest in multimodal, knowledge, math.
What is Qwen3-VL 235B-A22B best at?
Its best category is multimodal, where it ranks 55th on Noometry.