Model card
Qwen3.5-35B-A3B.
Alibabaopen-source
§ 02 · Benchmarks
Every benchmark Qwen3.5-35B-A3B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MMStar | Multimodal · Image-Text-to-Text | accuracy | 81.9% | #3 | — | source ↗ |
| 02 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 84.1% | #3 | — | source ↗ |
| 03 | Tau2-Bench | Agentic AI · Tool Use | accuracy | 81.2% | #4 | — | source ↗ |
| 04 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 81.4% | #7 | — | source ↗ |
| 05 | MVBench | Multimodal · Video Understanding | accuracy | 74.8% | #8 | — | source ↗ |
| 06 | BrowseComp | Natural Language Processing · Question Answering | accuracy | 61.0% | #9 | — | source ↗ |
| 07 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 75.1% | #12 | — | source ↗ |
| 08 | SWE-Bench Verified | Computer Code · Code Generation | accuracy | 69.2% | #17 | — | source ↗ |
| 09 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 84.2% | #24 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 66.0% | #61 | — | source ↗ |
| 11 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 73.0% | #83 | — | source ↗ |
| 12 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 57.0% | #98 | — | source ↗ |
| 13 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 68.0% | #100 | — | source ↗ |
| 14 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 44.0% | #103 | — | source ↗ |
| 15 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 45.0% | #105 | — | source ↗ |
| 16 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 46.0% | #115 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Qwen3.5-35B-A3B actually performs.
§ 04 · Papers
1 paper with results for Qwen3.5-35B-A3B.
- 2026-02-16· 9 results
Qwen3.5: Towards Native Multimodal Agents
§ 05 · Related models
Other Alibaba models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
9
results
sdadas/PLCC
7
results
7 of 16 rows marked verified.