Qwen 3.5 122B A10B — benchmark results
Alibaba's open Qwen 3.5 122B A10B MoE (10B active). Provider: Alibaba. Released 2026-02-24. Access: Open.
Unified ELO 1650 ± 10, rank #365 of 1776 rated models, from 179 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MVBench) | 76.6 | Score (%) | 100 |
| LLM Stats (VideoMME w/o sub.) | 83.9 | Score (%) | 100 |
| MATH-MC Level 5 | 99.92 | Accuracy (%) | 100 |
| LLM Stats (MMBench-V1.1) | 92.8 | Score (%) | 97.1 |
| RewardBench 2 Safety | 94.67 | Accuracy (%) | 96.1 |
| MATH-MC Level 4 | 99.58 | Accuracy (%) | 95.6 |
| SEA-HELM | 70.92 | Mean Score (%) | 95.3 |
| LLM Stats (MMStar) | 82.9 | Score (%) | 95.2 |
| LLM Stats (OCRBench) | 92.1 | Score (%) | 95.2 |
| RewardBench 2 Math | 90.71 | Accuracy (%) | 94.1 |
| SnakeBench | 33 | TrueSkill Rating | 94 |
| MathVision | 86.2 | Overall Accuracy (%) | 93.8 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-122b-a10b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.