Qwen 3.8 27B (Non-reasoning): benchmark results
Provider: Alibaba. Released 2026-08-14. Access: Open.
Aggregate Rating 1636 ± 18, rank #575 of 2168 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BRIDGE Medical Leaderboard - Few-Shot | 55.67 | Average Performance (%) | 99.1 |
| AA-Omniscience Hallucination Rate | 18.09 | Hallucination Rate (%) | 98.3 |
| BRIDGE Medical Leaderboard - Zero-Shot | 44.6 | Average Performance (%) | 95.5 |
| BRIDGE Medical Leaderboard - CoT | 42.94 | Average Performance (%) | 94.6 |
| AA-Omniscience Index - Health | -6.7 | Omniscience Index | 80.1 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | -8 | Omniscience Index | 75.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Dart | 6 | Omniscience Index | 75.2 |
| AA-Omniscience Index - Law | -8.1 | Omniscience Index | 72.3 |
| AA-Omniscience Index - Business | -8.4 | Omniscience Index | 71.3 |
| AA GPQA Diamond | 81.82 | Accuracy (%) | 69.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | -12 | Omniscience Index | 69.6 |
| AA Omniscience | -7.95 | Score | 69.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-27b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.