Qwen 3.5 27B Instruct: benchmark results
Provider: Alibaba. Released 2026-02-24.
Aggregate Rating 1620 ± 44, rank #829 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TAEF (Text Analytics Evaluation Framework) | 77.9 | F1 (self-reported) | 90 |
| Video-MME-v2 | 31.7 | Avg Accuracy w/o sub (%) | 62.5 |
| Video-MME-v2 - Level 2 Temporal Understanding (w/o subs) | 14.82 | Level 2 Score w/o sub (%) | 62.5 |
| Video-MME-v2 - Level 3 Complex Reasoning (w/o subs) | 12.34 | Level 3 Score w/o sub (%) | 60.4 |
| Video-MME-v2 - Non-Lin Score (w/o subs) | 14 | Non-Lin Score w/o sub (%) | 60.4 |
| Video-MME-v2 - Level 1 Retrieval & Aggregation (w/o subs) | 15.84 | Level 1 Score w/o sub (%) | 47.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-27b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.