Qwen 3.5 122B A10B (Reasoning): benchmark results
Qwen 3.5 122B A10B evaluated with reasoning enabled. Provider: Alibaba. Released 2026-02-24. Access: Open.
Aggregate Rating 1624 ± 10, rank #627 of 2168 rated models, from 232 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (English) - SuperGPQA | 63.33 | Normalized Score | 100 |
| SEA-HELM (Indonesian) - SEA-MT-Bench (LLM Judge) | 88.03 | Normalized Score | 100 |
| SEA-HELM (Malay) | 76.31 | Normalized Score | 100 |
| SEA-HELM (Malay) - SEA-MT-Bench (LLM Judge) | 86.35 | Normalized Score | 100 |
| SEA-HELM (Thai) - Sentiment Analysis | 42.82 | Normalized Score | 100 |
| SEA-HELM (English) - Knowledge | 77.79 | Normalized Score | 98.2 |
| SEA-HELM (English) - MMLU Redux | 92.25 | Normalized Score | 98.2 |
| SEA-HELM (Indonesian) - Causal Reasoning | 97.04 | Normalized Score | 98.2 |
| SEA-HELM (Indonesian) - Global MMLU Lite | 86.01 | Normalized Score | 98.2 |
| SEA-HELM (Indonesian) - NLR | 90.07 | Normalized Score | 98.2 |
| SEA-HELM (Malay) - Belebele QA | 93.94 | Normalized Score | 98.2 |
| SEA-HELM (Malay) - Global MMLU Lite | 85.99 | Normalized Score | 98.2 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-122b-a10b-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.