Qwen3-235B-A22B-Instruct-2507-awq: benchmark results
Provider: Alibaba.
Aggregate Rating 1615 ± 39, rank #882 of 10916 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TurkBench - Faithfulness | 89.07 | LLM-as-a-judge score (0-100) | 94.6 |
| TurkBench - Instruction Following | 94.54 | LLM-as-a-judge score (0-100) | 94.6 |
| TurkBench - Reading Comprehension | 95.4 | LLM-as-a-judge score (0-100) | 94.6 |
| TurkBench - Topic Detection | 87.65 | Accuracy (%) | 94.4 |
| TurkBench - Parts of Speech | 80.98 | Accuracy (%) | 89.2 |
| TurkBench - Summarization | 81.77 | LLM-as-a-judge score (0-100) | 86.5 |
| TurkBench - STS | 92.17 | Pearson correlation x100 | 78.4 |
| TurkBench - Truthfulness | 77.35 | LLM-as-a-judge score (0-100) | 73 |
| TurkBench - Commonsense Reasoning | 91.39 | Accuracy (%) | 70.3 |
| TurkBench - MMLU Topics | 61.58 | Accuracy (%) | 70.3 |
| TurkBench - Math | 47.2 | Accuracy (%) | 70.3 |
| TurkBench - Sentiment Analysis | 47.44 | Accuracy (%) | 64.9 |
Interactive version: theaggregate.ai/model?slug=qwen3-235b-a22b-instruct-2507-awq · How It Works · Data refreshed daily, snapshot 2026-11-08.