Qwen 2.5 0.5B: benchmark results
Alibaba's open Qwen 2.5 0.5B, the smallest model in the Qwen 2.5 family (September 2024). Provider: Alibaba. Released 2024-09-19. Access: Open.
Aggregate Rating 1234 ± 14, rank #1560 of 1656 rated models, from 280 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU Civics (High School) | 44.83 | Accuracy (%) | 56.5 |
| Open Japanese LLM - CG | 2.41 | Score (%) | 41 |
| Open Japanese LLM - Mbpp Pylint Check | 8.43 | Score (%) | 38 |
| Swallow - Pre-trained English - GSM8K | 34.1 | Exact Match (%) | 32.7 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 67.54 | Score (%) | 31 |
| Swallow - Pre-trained English - HumanEval | 27.7 | Pass@1 (%) | 30.6 |
| Open Japanese LLM - Xlsum JA Rouge1 | 20.76 | Score (%) | 29.1 |
| Open Japanese LLM - Xlsum JA RougeLsum | 17.84 | Score (%) | 28.7 |
| Swallow - Pre-trained English - MATH | 14.8 | Exact Match (%) | 28.6 |
| Open Arabic LLM - Arabic MMLU HT Machine Learning | 31.25 | Accuracy (%) | 27.2 |
| Open Japanese LLM - SUM | 7.47 | Score (%) | 27.2 |
| Open Japanese LLM - Xlsum JA Rouge2 | 7.48 | Score (%) | 27.2 |
Interactive version: theaggregate.ai/model?slug=qwen-2-5-0-5b · How It Works · Data refreshed daily, snapshot 2026-10-20.