Alibaba (Qwen), open weights
Qwen3.6 35B-A3B
Qwen3.6 35B-A3B by Alibaba (Qwen) ranks 201st of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.6. Its strongest category is knowledge, where it ranks 68th. API pricing starts at $0.25 per million input tokens and $1.49 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #201 of 354
- Index score
- 37.6
- Evidence
- Confirmed 14 results
- Provider
Alibaba (Qwen)- Released
- April 1, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 66K
- Input price
- $0.25 / M
- Output price
- $1.49 / M
- Blended price
- $0.56 / M
- Output speed
- Not measured
- Value
- #86 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image, video, audio
- Hugging Face
- Qwen/Qwen3.6-35B-A3B
Category scores
Each category score combines every public result we have in that category.
- Coding 37.2
- Agentic & Tool Use 22.1
- Reasoning 28.0
- Math 38.9
- Knowledge 51.3
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 37.2 | #196 | 2 |
| Agentic & Tool Use | 22.1 | #134 | 1 |
| Reasoning | 28.0 | #109 | 7 |
| Math | 38.9 | #121 | 2 |
| Knowledge | 51.3 | #68 | 1 |
Strengths and weaknesses
Categories where Qwen3.6 35B-A3B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 22.1 | −8.3 | #134 of 154, top 88% |
| Coding | 37.2 | −1.5 | #196 of 340, top 58% |
Closest competitors
The models ranked just above and below Qwen3.6 35B-A3B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini Advanced 0514 | #197 | 37.7 | — | — | Compare |
| Grok 2 Mini 2024 08 13 | #198 | 37.7 | — | — | Compare |
| Mercury | #199 | 37.6 | — | 35 | Compare |
| DeepSeek-V2.5 (Sep 2024) | #200 | 37.6 | — | — | Compare |
| Hunyuan Large Vision | #202 | 37.6 | — | — | Compare |
| Llama 3.1 Nemotron 70b Instruct | #203 | 37.6 | — | — | Compare |
| MiniMax-M2 | #204 | 37.4 | $0.52 | 17 | Compare |
| Granite 4.1 8b | #205 | 37.4 | — | — | 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 |
|---|---|---|---|---|---|
| SciCode | 35.8% | #96 of 121, top 80% | Epoch AI | ||
| SciCode | 1.3% | none | Epoch AI | ||
| WeirdML | 34.5% | #93 of 119, top 79% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | 23% | #36 of 41, top 88% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| NYT Connections (extended) | 41.6% | #65 of 91, top 72% | Lech Mazur benchmarks | ||
| CritPt | 0.3% | #100 of 134, top 75% | Epoch AI | ||
| CritPt | 0% | none | Epoch AI | ||
| Chess Puzzles | 26% | #42 of 129, top 33% | Epoch AI | 2026-08-07 | |
| Chess Puzzles | 4% | none | Epoch AI | 2026-08-07 | |
| Mystery Game Puzzles | 22% | #38 of 74, top 52% | none | Epoch AI | 2026-08-27 |
| DTBench | 73.9% | #89 of 151, top 59% | Epoch AI | ||
| LMCA | 29.7% | #72 of 125, top 58% | Epoch AI | ||
| Surface Evolver Bench | 44.4% | #19 of 25, top 76% | Epoch AI | ||
| Epoch Capabilities Index | 143.93 | #89 of 213, top 42% | Epoch AI | 2026-04-14 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 17.5% | Epoch AI | 2026-08-29 | ||
| FrontierMath (Tiers 1-3) | 20.4% | #68 of 81, top 84% | none | Epoch AI | 2026-08-30 |
| OTIS Mock AIME 2024-2025 | 86.7% | #65 of 173, top 38% | Epoch AI | 2026-08-07 | |
| OTIS Mock AIME 2024-2025 | 68.9% | none | Epoch AI | 2026-08-07 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 83.8% | Epoch AI | 2026-08-07 | ||
| GPQA Diamond | 84.8% | #66 of 186, top 36% | none | Epoch AI | 2026-08-07 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $0.25 | $1.49 | — | 2026-10-10 |
| deepinfra | $0.10 | $0.95 | $0.10 | 2026-10-10 |
| openrouter | $0.15 | $1 | $0.05 | 2026-10-10 |
Compare Qwen3.6 35B-A3B
- Qwen3.6 35B-A3B vs Qwen3.5 122B-A10B
- Qwen3.6 35B-A3B vs DeepSeek-V2.5 (Sep 2024)
- Qwen3.6 35B-A3B vs Hunyuan Large Vision
- Qwen3.6 35B-A3B vs Mercury
- Qwen3.6 35B-A3B vs Llama 3.1 Nemotron 70b Instruct
- Qwen3.6 35B-A3B vs Grok 2 Mini 2024 08 13
- Qwen3.6 35B-A3B vs MiniMax-M2
- Qwen3.6 35B-A3B vs GPT-6 Astra
- Qwen3.6 35B-A3B vs Claude Fable 5.1
- Qwen3.6 35B-A3B vs Gemini 3.8 Flash
- Qwen3.6 35B-A3B vs Kimi K3
- Qwen3.6 35B-A3B vs Grok 4.6
- Qwen3.6 35B-A3B vs GLM-5.3
- Qwen3.6 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 Qwen3.6 35B-A3B?
Qwen3.6 35B-A3B by Alibaba (Qwen) ranks 201st of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.6. Its strongest category is knowledge, where it ranks 68th. API pricing starts at $0.25 per million input tokens and $1.49 per million output tokens, with a 262K-token context window.
How much does Qwen3.6 35B-A3B cost?
Qwen3.6 35B-A3B costs $0.25 per million input tokens and $1.49 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen3.6 35B-A3B's context window?
Qwen3.6 35B-A3B accepts up to 262K tokens of input and can write up to 66K tokens in one response.
Is Qwen3.6 35B-A3B open source?
Yes. Qwen3.6 35B-A3B's weights are downloadable from Hugging Face (Qwen/Qwen3.6-35B-A3B); check the license for commercial terms.
What are Qwen3.6 35B-A3B's strengths and weaknesses?
Relative to other ranked models, Qwen3.6 35B-A3B places best in knowledge, reasoning and lowest in agentic & tool use, coding.
What is Qwen3.6 35B-A3B best at?
Its best category is knowledge, where it ranks 68th on Noometry.