Qwen 3.8 27B (Low): benchmark results
Provider: Alibaba. Released 2026-08-14. Access: Open.
Unified ELO 1628 ± 1, rank #327 of 1761 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 33.76 | Intelligence Index | 86.1 |
| AA Long Context Reasoning | 77.33 | Accuracy (%) | 81.7 |
| AA GDPval | 1407.51 | ELO | 77.6 |
| AA GPQA Diamond | 84.55 | Accuracy (%) | 76.6 |
| Tau3 Banking | 32.16 | Success Rate (%) | 72 |
| AA Humanity's Last Exam | 14.04 | Accuracy (%) | 64.7 |
| AA MMMU-Pro | 73.76 | Accuracy (%) | 63.8 |
| AA Omniscience | -26.67 | Score | 59.3 |
| AA Omniscience - Software Engineering (SWE) | 23.5 | Accuracy (%) | 44 |
| AA Omniscience - Science, Engineering & Mathematics | 25.9 | Accuracy (%) | 40.5 |
| AA Omniscience - Health | 17.7 | Accuracy (%) | 38.3 |
| AA-Omniscience Accuracy | 17.13 | Accuracy (%) | 35.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-27b-low · How It Works · Data refreshed daily, snapshot 2026-09-05.