Qwen 3.5 122B A10B (Non-reasoning) — benchmark results
Qwen 3.5 122B A10B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-24. Access: Open.
Unified ELO 1634 ± 28, rank #407 of 1776 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Global-MMLU-Lite - Indonesian | 89.58 | Accuracy (%) | 79.1 |
| AA GPQA Diamond | 82.73 | Accuracy (%) | 77.7 |
| UGI - Natural Intelligence | 31.08 | NatInt Score | 77.5 |
| AA Global-MMLU-Lite - Italian | 90.42 | Accuracy (%) | 77.2 |
| AA Global-MMLU-Lite - Yoruba | 71.08 | Accuracy (%) | 76.1 |
| AA TAU-2 Bench | 84.5 | Accuracy (%) | 75.7 |
| AA Global-MMLU-Lite - French | 89.83 | Accuracy (%) | 75.2 |
| AA Global-MMLU-Lite - Japanese | 88.08 | Accuracy (%) | 75.2 |
| AA Global-MMLU-Lite - Korean | 87 | Accuracy (%) | 75.2 |
| AA Humanity's Last Exam | 14.83 | Accuracy (%) | 73.3 |
| UGI - Writing | 39.54 | Writing Score | 72.3 |
| Artificial Analysis Intelligence Index | 27.6 | Intelligence Index | 72 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-122b-a10b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.