Qwen 3.5 397B A17B (Non-reasoning) — benchmark results
Qwen 3.5 397B A17B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-16. Access: Open.
Unified ELO 1684 ± 21, rank #303 of 1776 rated models, from 53 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 50.06 | Writing Score | 89 |
| UGI - Natural Intelligence | 41.01 | NatInt Score | 87.6 |
| AA GPQA Diamond | 86.06 | Accuracy (%) | 86.3 |
| AA Global-MMLU-Lite - Portuguese | 91.33 | Accuracy (%) | 84.8 |
| AA Terminal-Bench Hard | 35.61 | Accuracy (%) | 82 |
| AA Global-MMLU-Lite - Korean | 88 | Accuracy (%) | 80.9 |
| AA Humanity's Last Exam | 18.77 | Accuracy (%) | 78.7 |
| Artificial Analysis Intelligence Index | 31.98 | Intelligence Index | 78.4 |
| AA SciCode | 41.09 | Accuracy (%) | 78.2 |
| AA Global-MMLU-Lite - German | 89.75 | Accuracy (%) | 77.1 |
| AA Global-MMLU-Lite - Yoruba | 71.08 | Accuracy (%) | 76.1 |
| AA TAU-2 Bench | 83.92 | Accuracy (%) | 74.8 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-397b-a17b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.