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 2024-06-06. Access: Open.
Aggregate Rating 1431 ± 10, rank #1095 of 1656 rated models, from 173 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 72.93 | Accuracy (%) (5-shot) | 98.3 |
| Open LLM Leaderboard v1 - MMLU | 70.45 | Accuracy (%) (5-shot) | 94 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 57.24 | Exact match, flexible extract (%) | 91.4 |
| 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 (%) | 84.8 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 70.26 | Score (%) | 82.5 |
| Open Portuguese LLM - OAB Exams | 52.62 | Accuracy (%) | 82.3 |
| Open Chinese LLM - WinoGrande | 67.32 | Accuracy (%) | 81.8 |
| Open LLM Leaderboard - MuSR | 44.39 | Score | 80.3 |
| Open Japanese LLM - SUM | 10.93 | Score (%) | 79.8 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.93 | Score (%) | 79.8 |
Interactive version: theaggregate.ai/model?slug=qwen-2-7b · How It Works · Data refreshed daily, snapshot 2026-10-20.