Qwen 2 7B: benchmark results
Alibaba's Apache-2.0 7B Qwen2 base model (June 2024), the pretrained foundation for Qwen2-7B-Instruct. Provider: Alibaba. Released 2024-06-07. Access: Open.
Unified ELO 1463 ± 1, rank #884 of 1392 rated models, from 115 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Xlsum JA Rouge1 | 31 | Score (%) | 86.3 |
| Open Japanese LLM - Xlsum JA RougeLsum | 26.22 | Score (%) | 86.3 |
| Open Chinese LLM - GSM8K | 60.12 | Accuracy (%) | 84.7 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 70.26 | Score (%) | 82.5 |
| Open Chinese LLM - WinoGrande | 67.32 | Accuracy (%) | 81.8 |
| Open Japanese LLM - SUM | 10.93 | Score (%) | 79.8 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.93 | Score (%) | 79.8 |
| European LLM Leaderboard - Accuracy | 54.24 | Average Accuracy (%) | 78.4 |
| Open LLM Leaderboard - MuSR | 14.32 | Score | 78.3 |
| Open Chinese LLM Leaderboard | 63.5 | Average Score (%) | 76.6 |
| Open Chinese LLM - CMMLU | 64.4 | Accuracy (%) | 76.3 |
| Open LLM Leaderboard - MMLU-Pro | 35.37 | Score | 76 |
Interactive version: theaggregate.ai/model?slug=qwen-2-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.