Alibaba (Qwen), open weights
Qwen3.5 35B-A3B
Qwen3.5 35B-A3B by Alibaba (Qwen) ranks 123rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is knowledge, where it ranks 79th. API pricing starts at $0.25 per million input tokens and $2 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #123 of 354
- Index score
- 42.0
- Evidence
- Confirmed 28 results
- Provider
Alibaba (Qwen)- Released
- February 1, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 66K
- Input price
- $0.25 / M
- Output price
- $2 / M
- Blended price
- $0.69 / M
- Output speed
- Not measured
- Value
- #89 of 219
- Knowledge cutoff
- January 2025
- Input
- text, image, video, audio
- Hugging Face
- Qwen/Qwen3.5-35B-A3B
Category scores
Each category score combines every public result we have in that category.
- Coding 33.8
- Reasoning 24.6
- Math 39.9
- Knowledge 47.8
- Multilingual 50.0
- Instruction Following 72.8
- Long Context 42.4
- Writing & Preference 57.9
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 33.8 | #251 | 3 |
| Reasoning | 24.6 | #161 | 5 |
| Math | 39.9 | #97 | 3 |
| Knowledge | 47.8 | #79 | 3 |
| Multilingual | 50.0 | #127 | 1 |
| Instruction Following | 72.8 | #128 | 1 |
| Long Context | 42.4 | #127 | 1 |
| Writing & Preference | 57.9 | #124 | 3 |
Strengths and weaknesses
Categories where Qwen3.5 35B-A3B 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 |
|---|---|---|---|
| Knowledge | 47.8 | +10.5 | #79 of 314, top 26% |
| Math | 39.9 | +3.3 | #97 of 327, top 30% |
| Writing & Preference | 57.9 | +4.1 | #124 of 312, top 40% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 33.8 | −4.9 | #251 of 340, top 74% |
| Reasoning | 24.6 | +1.0 | #161 of 350, top 46% |
| Long Context | 42.4 | +1.4 | #127 of 296, top 43% |
Closest competitors
The models ranked just above and below Qwen3.5 35B-A3B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Qwen3.5 122B-A10B | #119 | 42.1 | $1.10 | — | 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 |
| GLM-4.7 | #124 | 42.0 | $1 | — | Compare |
| GPT-5.4 nano | #125 | 41.9 | $0.46 | 19 | Compare |
| Amazon Nova Experimental Chat 10 09 | #126 | 41.9 | — | — | Compare |
| Qwen3.5 27B | #127 | 41.9 | $0.82 | — | 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 | 1254 | #101 of 113, top 90% | LMArena | 2026-10-08 | |
| SciCode | 29.3% | #106 of 121, top 88% | none | Epoch AI | |
| LMArena Coding | 1410 | #129 of 294, top 44% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| CritPt | 0.6% | #90 of 134, top 68% | none | Epoch AI | |
| Chess Puzzles | 1% | Epoch AI | 2026-08-28 | ||
| Chess Puzzles | 10% | #83 of 129, top 65% | none | Epoch AI | 2026-08-30 |
| LMArena Hard Prompts | 1400 | #125 of 297, top 43% | LMArena | 2026-10-08 | |
| DTBench | 80% | #77 of 151, top 51% | Epoch AI | ||
| LMCA | 29.5% | #75 of 125, top 60% | Epoch AI | ||
| Epoch Capabilities Index | 142.52 | #97 of 213, top 46% | Epoch AI | 2026-02-24 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| MathArena Final-Answer Competitions | 56% | #26 of 29, top 90% | MathArena | ||
| OTIS Mock AIME 2024-2025 | 54.4% | Epoch AI | 2026-08-30 | ||
| OTIS Mock AIME 2024-2025 | 70% | #93 of 173, top 54% | none | Epoch AI | 2026-08-30 |
| LMArena Math | 1404 | #121 of 285, top 43% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 83.5% | #68 of 186, top 37% | Epoch AI | 2026-08-28 | |
| GPQA Diamond | 81.2% | none | Epoch AI | 2026-08-28 | |
| Vectara Hallucination Rate (lower is better) | 10.5% | #59 of 96, top 62% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1408 | #116 of 273, top 43% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1378 | #127 of 297, top 43% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1457 | #95 of 285, top 34% | LMArena | 2026-10-08 | |
| LMArena French | 1412 | #110 of 223, top 50% | LMArena | 2026-10-08 | |
| LMArena German | 1367 | #119 of 231, top 52% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1325 | #112 of 211, top 54% | LMArena | 2026-10-08 | |
| LMArena Korean | 1356 | #101 of 213, top 48% | LMArena | 2026-10-08 | |
| LMArena Russian | 1376 | #131 of 283, top 47% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1392 | #118 of 226, top 53% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1379 | #122 of 298, top 41% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1389 | #128 of 291, top 44% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1395 | #125 of 297, top 43% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1346 | #132 of 295, top 45% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1390 | #128 of 295, top 44% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $0.25 | $2 | — | 2026-10-10 |
| deepinfra | $0.14 | $1 | $0.05 | 2026-10-10 |
| openrouter | $0.08 | $0.75 | $0.04 | 2026-10-10 |
Compare Qwen3.5 35B-A3B
- Qwen3.5 35B-A3B vs Qwen3-4B
- Qwen3.5 35B-A3B vs GLM-4.5
- Qwen3.5 35B-A3B vs GLM-4.7
- Qwen3.5 35B-A3B vs Solar Pro4
- Qwen3.5 35B-A3B vs GPT-5.4 nano
- Qwen3.5 35B-A3B vs Longcat Flash Chat
- Qwen3.5 35B-A3B vs Amazon Nova Experimental Chat 10 09
- Qwen3.5 35B-A3B vs GPT-6 Astra
- Qwen3.5 35B-A3B vs Claude Fable 5.1
- Qwen3.5 35B-A3B vs Gemini 3.8 Flash
- Qwen3.5 35B-A3B vs Kimi K3
- Qwen3.5 35B-A3B vs Grok 4.6
- Qwen3.5 35B-A3B vs GLM-5.3
- Qwen3.5 35B-A3B 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 35B-A3B?
Qwen3.5 35B-A3B by Alibaba (Qwen) ranks 123rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is knowledge, where it ranks 79th. API pricing starts at $0.25 per million input tokens and $2 per million output tokens, with a 262K-token context window.
How much does Qwen3.5 35B-A3B cost?
Qwen3.5 35B-A3B costs $0.25 per million input tokens and $2 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen3.5 35B-A3B's context window?
Qwen3.5 35B-A3B accepts up to 262K tokens of input and can write up to 66K tokens in one response.
Is Qwen3.5 35B-A3B open source?
Yes. Qwen3.5 35B-A3B's weights are downloadable from Hugging Face (Qwen/Qwen3.5-35B-A3B); check the license for commercial terms.
What are Qwen3.5 35B-A3B's strengths and weaknesses?
Relative to other ranked models, Qwen3.5 35B-A3B places best in knowledge, math, writing & preference and lowest in coding, reasoning, long context.
What is Qwen3.5 35B-A3B best at?
Its best category is knowledge, where it ranks 79th on Noometry.