Qwen3.5 35B-A3B is a sparse mixture-of-experts model from Alibaba's Qwen3.5 line (35B total, 3B active parameters), built for efficient general-purpose and agentic tasks at low inference cost.
Cost rate
0.2x
Context
262K
Released
Feb 25, 2026
Input
TextImageVideo
Output
Text
Support
ReasoningTool callingStructured outputs
Performance
Median latency and throughput measured across recent requests.
Throughput105 tok/s
Latency3.69s
Best at
The categories where this model ranks highest.
Medicine & Healthcare
#159 路 top 41%
Business, Management, & Finance
#168 路 top 40%
Life, Physical, & Social Science
#170 路 top 40%
Mathematical
#170 路 top 42%
| Domain | Score | Rank |
|---|---|---|
| CodingCode Arena Elo | 1253 | #147 |
| Software & IT Services | 1430 | #173 |
| Writing, Literature, & Language | 1364 | #186 |
| Life, Physical, & Social Science | 1416 | #170 |
| Entertainment, Sports, & Media | 1345 | #192 |
| Business, Management, & Finance | 1403 | #168 |
| Mathematical | 1409 | #170 |
| Legal & Government | 1399 | #174 |
| Medicine & Healthcare | 1427 | #159 |
Latest news about Qwen3.5-35B-A3B
Recent articles and community posts, linked to their original sources.
Mapping every neuron in Qwen3-8BHacker News302
Doubling Qwen Flash Next speed with Strata HotRodNo place like localhost18,864
Qwen 4 Max is here! OpenAI and Anthropic are in troubleSimon H酶iberg17,830
Qwen4 Max Just Dropped, China's New BEST AI Model!AI Revolution84,709
Qwen 4 Max IS OUT! BEST Chinese AI Model EVER?! (Fully Tested)WorldofAI120,344
Qwen4-MaxHacker News883485