Model card
Qwen3.5-122B-A10B.
Alibabaopen-source
§ 02 · Benchmarks
Every benchmark Qwen3.5-122B-A10B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 83.9% | #2 | — | source ↗ |
| 02 | MMStar | Multimodal · Image-Text-to-Text | accuracy | 82.9% | #2 | — | source ↗ |
| 03 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 85.1% | #2 | — | source ↗ |
| 04 | MVBench | Multimodal · Video Understanding | accuracy | 76.6% | #3 | — | source ↗ |
| 05 | BrowseComp | Natural Language Processing · Question Answering | accuracy | 63.8% | #7 | — | source ↗ |
| 06 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 76.9% | #7 | — | source ↗ |
| 07 | Tau2-Bench | Agentic AI · Tool Use | accuracy | 79.5% | #7 | — | source ↗ |
| 08 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 86.6% | #13 | — | source ↗ |
| 09 | SWE-Bench Verified | Computer Code · Code Generation | accuracy | 72.0% | #15 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 73.0% | #39 | — | source ↗ |
| 11 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 83.0% | #50 | — | source ↗ |
| 12 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 78.0% | #66 | — | source ↗ |
| 13 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 61.0% | #66 | — | source ↗ |
| 14 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 68.3% | #68 | — | source ↗ |
| 15 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 62.0% | #83 | — | source ↗ |
| 16 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 53.0% | #84 | — | 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 Qwen3.5-122B-A10B actually performs.
§ 04 · Papers
1 paper with results for Qwen3.5-122B-A10B.
- 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.