Qwen 3.8 27B (xHigh): benchmark results
Provider: Alibaba. Released 2026-08-14. Access: Open.
Unified ELO 1668 ± 1, rank #187 of 1761 rated models, from 48 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Tau3 Banking | 48.04 | Success Rate (%) | 97.5 |
| AA Long Context Reasoning | 82 | Accuracy (%) | 94.9 |
| Vals AI SAGE | 52.4 | Accuracy (%) | 93.7 |
| Artificial Analysis Intelligence Index | 41.65 | Intelligence Index | 91.6 |
| AA GPQA Diamond | 90.51 | Accuracy (%) | 90.4 |
| Vals AI Harvey Legal Agent Bench | 11.25 | Accuracy (%) | 90.4 |
| AA-LCR | 77.33 | Accuracy (self-reported) | 88.4 |
| AA Humanity's Last Exam | 33.92 | Accuracy (%) | 85.9 |
| AA GDPval | 1467.93 | ELO | 84 |
| Vals AI SWE-bench Verified | 86 | Resolved (%) | 83.9 |
| AA CritPt | 5.43 | Accuracy (%) | 79.5 |
| Vals AI GPQA | 88.89 | Accuracy (%) | 77 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8-27b-xhigh · How It Works · Data refreshed daily, snapshot 2026-09-05.