Qwen 3.8 27B (Non-reasoning): benchmark results
Provider: Alibaba. Released 2026-08-14. Access: Open.
Unified ELO 1612 ± 1, rank #375 of 1761 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BRIDGE Medical Leaderboard - Few-Shot | 55.67 | Average Performance (%) | 100 |
| BRIDGE Medical Leaderboard | 47.74 | Average Performance (%) | 98.1 |
| BRIDGE Medical Leaderboard - Zero-Shot | 44.6 | Average Performance (%) | 97.2 |
| BRIDGE Medical Leaderboard - CoT | 42.94 | Average Performance (%) | 96.3 |
| Artificial Analysis Intelligence Index | 26.45 | Intelligence Index | 75.2 |
| AA Omniscience | -7.95 | Score | 75 |
| AA GPQA Diamond | 81.82 | Accuracy (%) | 69.9 |
| AA Long Context Reasoning | 69.33 | Accuracy (%) | 65.6 |
| AA Humanity's Last Exam | 12.14 | Accuracy (%) | 61.2 |
| AA GDPval | 1143.29 | ELO | 59.5 |
| AA CritPt | 0.29 | Accuracy (%) | 53.2 |
| Tau3 Banking | 20 | Success Rate (%) | 52.5 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-27b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.