Qwen 1.5 32B Chat: benchmark results
Alibaba's dense 32B chat model in the Qwen1.5 line (32K context, April 2024), released under the custom commercial-use Qwen license. Provider: Alibaba. Released 2024-04-02. Access: Open.
Aggregate Rating 1488 ± 11, rank #816 of 1656 rated models, from 259 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Knowledge - Social Science - Chinese (CompassBench 2405) | 73.1 | Score (%) | 97.4 |
| OpenCompass LLM - Language - English (CompassBench 2405) | 60 | Score (%) | 97.4 |
| Open Chinese LLM - C-Eval Semantic | 90.78 | Accuracy (%) | 97 |
| Open LLM Leaderboard v1 - MMLU | 74.99 | Accuracy (%) (5-shot) | 96.5 |
| OpenCompass Language - Content Critique - English (CompassBench 2405) | 56 | Score (%) | 96.1 |
| OpenCompass Language - Intention Recognition - Chinese (CompassBench 2405) | 76.3 | Score (%) | 96.1 |
| Open Chinese LLM - HellaSwag | 70.43 | Accuracy (%) | 94.7 |
| OpenCompass Knowledge - Natural Science - Chinese (CompassBench 2405) | 60.4 | Score (%) | 94.7 |
| OpenCompass LLM - Knowledge - Chinese (CompassBench 2405) | 65.9 | Score (%) | 94.7 |
| OpenCompass LLM - Language (CompassBench 2405) | 60.9 | Score (%) | 94.7 |
| OpenCompass Language - Chinese Semantic Understanding - Chinese (CompassBench 2405) | 76.7 | Score (%) | 94.7 |
| Open PL LLM - PSC (generative, 5-shot) | 98.2 | Binary F1 (%) | 93.6 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-32b-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.