Qwen 1.5 7B Chat: benchmark results
Provider: Alibaba. Released 2024-02-05. Access: Open.
Unified ELO 1398 ± 1, rank #1139 of 1392 rated models, from 127 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Reasoning | 90.41 | Accuracy (%) | 74 |
| ChineseSafe Benchmark | 70.36 | Accuracy (%) | 70.4 |
| BiGGen-Bench | 3.56 | Average Score (1-5) | 63.7 |
| RewardBench Chat Hard | 69.08 | Accuracy (%) | 63.6 |
| MERA - RWSD | 58.46 | Accuracy (%) | 62.4 |
| Open LLM Leaderboard - GPQA | 7.05 | Score | 59.2 |
| OpenEval - BBQ | 76.58 | Exact Match (%) | 54.5 |
| SALAD-Bench Base | 93 | Safety Score (%) | 51.5 |
| RewardBench | 67.5 | Score (%) | 47.5 |
| Open LLM Leaderboard - IFEval | 43.71 | Score | 46.6 |
| MERA - SimpleAr | 97.3 | EM (%) | 45.7 |
| MAGI-Hard | 41.59 | Accuracy (%, 2024-05 snapshot) | 44.8 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-7b-chat · How It Works · Data refreshed daily, snapshot 2026-09-05.