Qwen3 235B A22B Thinking (2507): benchmark results
Provider: Alibaba. Released 2025-07-25. Access: Open.
Aggregate Rating 1647 ± 41, rank #642 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RAI-Bench - Refusal Rate (General) | 86 | Rate (%) | 100 |
| RAI-Bench - RAG Robustness (HY Factuality) | 44 | Rate (%) | 87.5 |
| RAI-Bench - Refusal Rate (JD) | 96 | Rate (%) | 87 |
| RAI-Bench - Refusal Rate (Career) | 98 | Rate (%) | 83.6 |
| RAI-Bench - RAG Robustness (LC Factuality) | 44 | Rate (%) | 73.5 |
| RAI-Bench - Refusal Rate (Physics) | 100 | Rate (%) | 63.2 |
| RAI-Bench - RAG Robustness (HY Abstention) | 84 | Rate (%) | 60.3 |
| ObviousBench | 94.44 | Answer pass³ (%) | 55.7 |
| PLawBench | 62.82 | Overall (imported) | 50 |
| RAI-Bench - RAG Robustness (LC Abstention) | 76 | Rate (%) | 35.3 |
| OpenRouter GPQA Diamond | 76.2 | Accuracy (%) | 34.7 |
| LM Market Cap LMC Score | 64.7 | LMC Score (0-100) | 29.2 |
Interactive version: theaggregate.ai/model?slug=qwen3-235b-a22b-thinking-2507 · How It Works · Data refreshed daily, snapshot 2026-11-08.