Alibaba (Qwen), open weights
Qwen3.5 122B-A10B
Qwen3.5 122B-A10B by Alibaba (Qwen) ranks 119th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.1. Its strongest category is multimodal, where it ranks 57th. API pricing starts at $0.40 per million input tokens and $3.20 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #119 of 354
- Index score
- 42.1
- Evidence
- Confirmed 27 results
- Provider
Alibaba (Qwen)- Released
- February 23, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 66K
- Input price
- $0.40 / M
- Output price
- $3.20 / M
- Blended price
- $1.10 / M
- Output speed
- Not measured
- Value
- #124 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image, video, audio
- Hugging Face
- Qwen/Qwen3.5-122B-A10B
Category scores
Each category score combines every public result we have in that category.
- Coding 39.1
- Reasoning 27.2
- Math 39.1
- Knowledge 38.8
- Multimodal 39.6
- Multilingual 51.6
- Instruction Following 73.8
- Long Context 43.0
- Writing & Preference 60.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 39.1 | #162 | 3 |
| Reasoning | 27.2 | #123 | 7 |
| Math | 39.1 | #112 | 1 |
| Knowledge | 38.8 | #142 | 2 |
| Multimodal | 39.6 | #57 | 1 |
| Multilingual | 51.6 | #107 | 1 |
| Instruction Following | 73.8 | #115 | 1 |
| Long Context | 43.0 | #109 | 1 |
| Writing & Preference | 60.0 | #105 | 3 |
Strengths and weaknesses
Categories where Qwen3.5 122B-A10B 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 |
|---|---|---|---|
| Writing & Preference | 60.0 | +6.2 | #105 of 312, top 34% |
| Math | 39.1 | +2.6 | #112 of 327, top 35% |
| Reasoning | 27.2 | +3.6 | #123 of 350, top 36% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 39.1 | +0.4 | #162 of 340, top 48% |
| Knowledge | 38.8 | +1.5 | #142 of 314, top 46% |
| Multimodal | 39.6 | +1.1 | #57 of 128, top 45% |
Closest competitors
The models ranked just above and below Qwen3.5 122B-A10B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| DeepSeek-R1 | #115 | 42.3 | $0.91 | 10 | Compare |
| Step 3.5 Flash | #116 | 42.3 | $0.15 | — | Compare |
| Qwen3.6 27B | #117 | 42.2 | $1.35 | — | Compare |
| Amazon Nova Experimental Chat 10 20 | #118 | 42.1 | — | — | Compare |
| Longcat Flash Chat | #120 | 42.1 | — | 69 | Compare |
| Solar Pro4 | #121 | 42.1 | $0.52 | — | Compare |
| GLM-4.5 | #122 | 42.0 | $1 | 32 | Compare |
| Qwen3.5 35B-A3B | #123 | 42.0 | $0.69 | — | 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 WebDev | 1360 | #84 of 113, top 75% | LMArena | 2026-10-08 | |
| SciCode | 35.6% | #98 of 121, top 81% | none | Epoch AI | |
| LMArena Coding | 1436 | #104 of 294, top 36% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| NYT Connections (extended) | 51.7% | #62 of 91, top 69% | Lech Mazur benchmarks | ||
| CritPt | 0.9% | #84 of 134, top 63% | none | Epoch AI | |
| Thematic Generalization | 51.2% | #16 of 23, top 70% | Lech Mazur benchmarks | ||
| LMArena Hard Prompts | 1421 | #104 of 297, top 36% | LMArena | 2026-10-08 | |
| Mystery Game Puzzles | 17% | #51 of 74, top 69% | none | Epoch AI | 2026-08-27 |
| DTBench | 84.3% | #56 of 151, top 38% | none | Epoch AI | |
| LMCA | 32.2% | #69 of 125, top 56% | none | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1432 | #82 of 285, top 29% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 11.2% | #67 of 96, top 70% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1432 | #94 of 273, top 35% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1245 | #61 of 122, top 50% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1400 | #106 of 297, top 36% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1462 | #88 of 285, top 31% | LMArena | 2026-10-08 | |
| LMArena French | 1442 | #82 of 223, top 37% | LMArena | 2026-10-08 | |
| LMArena German | 1426 | #71 of 231, top 31% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1367 | #89 of 211, top 43% | LMArena | 2026-10-08 | |
| LMArena Korean | 1352 | #103 of 213, top 49% | LMArena | 2026-10-08 | |
| LMArena Russian | 1400 | #104 of 283, top 37% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1424 | #87 of 226, top 39% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1399 | #108 of 298, top 37% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1410 | #106 of 291, top 37% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1417 | #100 of 297, top 34% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1368 | #112 of 295, top 38% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1416 | #100 of 295, top 34% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $0.40 | $3.20 | — | 2026-10-10 |
| deepinfra | $0.29 | $2.40 | — | 2026-10-10 |
| openrouter | $0.26 | $2.08 | — | 2026-10-10 |
Compare Qwen3.5 122B-A10B
- Qwen3.5 122B-A10B vs Qwen3.5 397B-A17B
- Qwen3.5 122B-A10B vs Amazon Nova Experimental Chat 10 20
- Qwen3.5 122B-A10B vs Longcat Flash Chat
- Qwen3.5 122B-A10B vs Qwen3.6 27B
- Qwen3.5 122B-A10B vs Solar Pro4
- Qwen3.5 122B-A10B vs Step 3.5 Flash
- Qwen3.5 122B-A10B vs GLM-4.5
- Qwen3.5 122B-A10B vs GPT-6 Astra
- Qwen3.5 122B-A10B vs Claude Fable 5.1
- Qwen3.5 122B-A10B vs Gemini 3.8 Flash
- Qwen3.5 122B-A10B vs Kimi K3
- Qwen3.5 122B-A10B vs Grok 4.6
- Qwen3.5 122B-A10B vs GLM-5.3
- Qwen3.5 122B-A10B vs Muse Spark 1.3
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 Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B by Alibaba (Qwen) ranks 119th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.1. Its strongest category is multimodal, where it ranks 57th. API pricing starts at $0.40 per million input tokens and $3.20 per million output tokens, with a 262K-token context window.
How much does Qwen3.5 122B-A10B cost?
Qwen3.5 122B-A10B costs $0.40 per million input tokens and $3.20 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen3.5 122B-A10B's context window?
Qwen3.5 122B-A10B accepts up to 262K tokens of input and can write up to 66K tokens in one response.
Is Qwen3.5 122B-A10B open source?
Yes. Qwen3.5 122B-A10B's weights are downloadable from Hugging Face (Qwen/Qwen3.5-122B-A10B); check the license for commercial terms.
What are Qwen3.5 122B-A10B's strengths and weaknesses?
Relative to other ranked models, Qwen3.5 122B-A10B places best in writing & preference, math, reasoning and lowest in coding, knowledge, multimodal.
What is Qwen3.5 122B-A10B best at?
Its best category is multimodal, where it ranks 57th on Noometry.