Qwen 3.5 27B (Non-reasoning): benchmark results
Qwen 3.5 27B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-24. Access: Open.
Aggregate Rating 1606 ± 8, rank #693 of 2168 rated models, from 263 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Cloud-OpsBench (OnlineBoutique) - Evidence-Order Consistency | 70 | Evidence-order consistency (%): mean share of milestone grou | 100 |
| Cloud-OpsBench (OnlineBoutique) - Milestone Coverage | 75 | Milestone coverage (%): mean share of the case's expert diag | 100 |
| DistortBench | 61.9 | Joint accuracy (%) on DistortBench's 13,500 four-choice ques | 100 |
| DistortBench - Color | 58.3 | Joint accuracy (%) on the five color distortions (diffusion, | 100 |
| DistortBench - Luminance | 59.2 | Joint accuracy (%) on the four luminance distortions (bright | 100 |
| DistortBench - Noise | 65.7 | Joint accuracy (%) on the five noise distortions (white, col | 100 |
| DistortBench - Spatial | 64.8 | Joint accuracy (%) on the eight spatial distortions (jitter, | 100 |
| SVFSearch - RAG Workflow | 69.4 | Accuracy (%) on the 5,000-item SVFSearch test split (four-ch | 100 |
| Video-HOCA - Category Attribution (Causal) | 65.2 | Macro-F1 (%) of attributing each anomalous video to one of t | 100 |
| Video-HOCA - Fine-grained Recognition (Causal) | 85.7 | Macro-F1 (%) of choosing the correct anomaly description amo | 100 |
| Video-HOCA - Fine-grained Recognition (Ontological) | 90.2 | Macro-F1 (%) of choosing the correct anomaly description amo | 100 |
| OVO-S-Bench - Allocentric Spatial Mapping | 47.72 | Level 4 (allocentric spatial mapping: global direction, topo | 96.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-27b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.