qwen3:32B [Q4_K_M]: benchmark results
Provider: Alibaba.
Aggregate Rating 1571 ± 46, rank #1385 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Turkish MMLU - Driving Licence Exam | 93 | Accuracy (%) | 96.6 |
| Turkish MMLU - TUS | 81 | Accuracy (%) | 94.8 |
| Turkish MMLU | 75.98 | Accuracy (%) | 93.8 |
| Turkish MMLU - KPSS | 58 | Accuracy (%) | 92.2 |
| Turkish MMLU - University Entrance Exam Basic Sciences | 70 | Accuracy (%) | 87.1 |
| LLMStructBench | 0.67 | Composite score (0-1): the mean of micro-averaged key-value | 59.1 |
| RFMC - English-Chinese | 89.36 | COMET-22 (x100; document-level mean over 1,143 medical-domai | 58.3 |
| LLMStructBench - Document Correctness | 0.39 | Document correctness (0-1): share of tests whose JSON object | 56.8 |
| RFMC - English-Japanese | 89.02 | COMET-22 (x100; document-level mean over 1,143 medical-domai | 36.4 |
| RFMC - English-Russian | 88.07 | COMET-22 (x100; document-level mean over 1,143 medical-domai | 33.3 |
| RFMC - English-German | 87.31 | COMET-22 (x100; document-level mean over 1,143 medical-domai | 28.6 |
Interactive version: theaggregate.ai/model?slug=qwen3-32b-q4-k-m · How It Works · Data refreshed daily, snapshot 2026-11-08.