Qwen 2 0.5B Instruct: benchmark results
Alibaba's instruction-tuned 0.5B model in the Qwen2 series, post-trained with supervised fine-tuning and direct preference optimization on top of base Qwen2 pretraining. Provider: Alibaba. Released 2024-06-06. Access: Open.
Aggregate Rating 1237 ± 15, rank #1557 of 1656 rated models, from 257 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU LAW (Professional) | 66.56 | Accuracy (%) | 55.9 |
| Open Arabic LLM - Arabic MMLU Arabic Language (High School) | 32.82 | Accuracy (%) | 45.4 |
| Open Arabic LLM - Arabic MMLU HT College Chemistry | 34 | Accuracy (%) | 44.4 |
| Open Arabic LLM - Arabic MMLU HT Global Facts | 32 | Accuracy (%) | 44.1 |
| Open Portuguese LLM - FaQuAD NLI | 57.35 | Macro F1 (%) | 40.7 |
| Open Arabic LLM - Arabic MMLU Biology (High School) | 37.47 | Accuracy (%) | 38.3 |
| Open Arabic LLM - Arabic MMLU HT High School Mathematics | 26.3 | Accuracy (%) | 38 |
| Open Arabic LLM - Arabic MMLU Accounting (University) | 45.95 | Accuracy (%) | 37.7 |
| Open Arabic LLM - Arabic MMLU HT College Mathematics | 28 | Accuracy (%) | 37.3 |
| MERA - LCS | 11.2 | Accuracy (%) | 36 |
| Open Arabic LLM - Arabic MMLU HT Moral Scenarios | 24.25 | Accuracy (%) | 34.6 |
| Open Arabic LLM - Arabic MMLU HT Virology | 36.14 | Accuracy (%) | 34.6 |
Interactive version: theaggregate.ai/model?slug=qwen-2-0-5b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.