Qwen 1.5 0.5B: benchmark results
Alibaba's Qwen1.5-0.5B base model, the beta version of Qwen2, supporting a 32K context window as part of an eight-size family from 0.5B to 72B parameters. Provider: Alibaba. Released 2024-02-04. Access: Open.
Aggregate Rating 1207 ± 18, rank #1578 of 1656 rated models, from 153 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Mbpp Pylint Check | 14.26 | Score (%) | 42.7 |
| Open LLM Leaderboard v1 - GSM8K | 16.3 | Accuracy (%) (5-shot) | 38.1 |
| Open Japanese LLM - CG | 1.41 | Score (%) | 36.8 |
| Open Portuguese LLM - FaQuAD NLI | 52.54 | Macro F1 (%) | 34.2 |
| MERA - RWSD | 52.31 | Accuracy (%) | 30.7 |
| EuroEval Spanish NLU - ScaLA ES | 1.58 | Matthews correlation coefficient (%) | 30.4 |
| SALAD-Bench Attack | 7.78 | Safety Score (%) | 30.3 |
| MERA - LCS | 10.2 | Accuracy (%) | 27.9 |
| EuroEval Faroese NLU - ScaLA FO | 0.45 | Matthews correlation coefficient (%) | 24.7 |
| MERA - ruCodeEval | 0.3 | pass@1 (%) | 24.5 |
| SALAD-Bench | 44.07 | Average Safety Score (%) | 21.2 |
| SALAD-Bench Base | 80.36 | Safety Score (%) | 21.2 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-0-5b · How It Works · Data refreshed daily, snapshot 2026-10-20.