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 1639 ± 1, rank #151 of 1392 rated models, from 317 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (VideoMME w/o sub.) | 83.9 | Score (%) | 100 |
| MATH-MC Level 5 | 99.92 | Accuracy (%) | 100 |
| MERA - RWSD | 90.77 | Accuracy (%) | 99 |
| MERA - BPS | 100 | Accuracy (%) | 98.6 |
| MERA - ruModAr | 99.93 | EM (%) | 98.6 |
| Nejumi 4 - ALT Average | 90.78 | Score (%) | 98.4 |
| SEA-HELM (Malay) | 74.54 | Mean Score | 97.7 |
| MERA - USE | 71.47 | Grade, normalized (%) | 97.6 |
| MERA - ruHateSpeech | 92.83 | Accuracy (%) | 97.6 |
| LLM Stats (MMBench-V1.1) | 92.8 | Score (%) | 97.4 |
| MERA - MaMuRAMu | 90.21 | Accuracy (%) | 96.7 |
| Nejumi 4 - ALT - Bias | 97.14 | Score (%) | 96.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-122b-a10b · How It Works · Data refreshed daily, snapshot 2026-09-05.