Qwen 3.5 35B A3B Instruct: benchmark results
Provider: Alibaba. Released 2026-02-24.
Aggregate Rating 1586 ± 35, rank #1169 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Video-MME-v2 | 28.6 | Avg Accuracy w/o sub (%) | 46.9 |
| VideoJev Evaluation - Video-MME test without subtitles | 74.4 | Accuracy (%) | 44.4 |
| Video-MME-v2 - Level 2 Temporal Understanding (w/o subs) | 11.33 | Level 2 Score w/o sub (%) | 41.7 |
| Video-MME-v2 - Level 3 Complex Reasoning (w/o subs) | 9.94 | Level 3 Score w/o sub (%) | 37.5 |
| VideoJev Evaluation - LVBench test without subtitles | 58.8 | Accuracy (%) | 36.8 |
| VideoJev Evaluation - MLVU development MCQ | 77.4 | Accuracy (%) | 33.3 |
| Video-MME-v2 - Non-Lin Score (w/o subs) | 11.3 | Non-Lin Score w/o sub (%) | 26 |
| VideoJev Evaluation - LongVideoBench validation without subtitles | 65.7 | Accuracy (%) | 18.8 |
| Video-MME-v2 - Level 1 Retrieval & Aggregation (w/o subs) | 13.67 | Level 1 Score w/o sub (%) | 16.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-35b-a3b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.