Qwen 1.5 72B Chat: benchmark results
Alibaba's 72B Qwen1.5 chat model (February 2024) with 32K context and strong multilingual coverage. Provider: Alibaba. Released 2024-02-04. Access: Open.
Aggregate Rating 1502 ± 11, rank #776 of 1656 rated models, from 600 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - C-Eval Semantic | 91.14 | Accuracy (%) | 98.2 |
| Open Chinese LLM - HellaSwag | 72.16 | Accuracy (%) | 96.4 |
| Open Chinese LLM Leaderboard | 70.48 | Official Nonzero-Task Mean (%) | 95.6 |
| OpenCompass Knowledge - Common Sense - Chinese (CompassBench 2405) | 78.7 | Score (%) | 94.7 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 92.36 | Binary F1 (%) | 94.4 |
| OpenCompass Knowledge - Social Science - Chinese (CompassBench 2405) | 71.8 | Score (%) | 92.1 |
| OpenCompass LLM - Knowledge - Chinese (CompassBench 2405) | 64 | Score (%) | 92.1 |
| Open Chinese LLM - ARC Challenge | 62.12 | Accuracy (%) | 91.9 |
| Open Portuguese LLM - ENEM | 77.05 | Accuracy (%) | 90.7 |
| Open Portuguese LLM - BLUEX | 67.59 | Accuracy (%) | 90.1 |
| OpenCompass Knowledge - Humanities - Chinese (CompassBench 2405) | 53.7 | Score (%) | 89.5 |
| OpenCompass LLM - Knowledge (CompassBench 2405) | 70.4 | Score (%) | 89.5 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-72b-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.