Qwen2-1.5B-Ita: benchmark results
Provider: Alibaba. Released 2024-06-13. Access: Open.
Unified ELO 1365 ± 1, rank #1232 of 1392 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Pinocchio Italian - Lingua Straniera | 71.84 | Accuracy (%) | 72.7 |
| Open LLM Leaderboard - IFEval | 51.73 | Score | 61.6 |
| Open LLM Leaderboard - MATH Level 5 | 11.4 | Score | 51.8 |
| Pinocchio Italian - Diritto | 49.32 | Accuracy (%) | 45.5 |
| Pinocchio Italian Leaderboard | 49.67 | Average Accuracy (%) | 43.2 |
| Pinocchio Italian - Generale | 50.09 | Accuracy (%) | 40.9 |
| Open Italian LLM - MMLU-Pro (IT) | 20.31 | Accuracy (%) | 32.1 |
| Pinocchio Italian - Cultura | 48.65 | Accuracy (%) | 31.8 |
| Pinocchio Italian - Logica | 37.6 | Accuracy (%) | 31.8 |
| Open LLM Leaderboard - MMLU-Pro | 19.69 | Score | 30.3 |
| Pinocchio Italian - Matematica E Scienze | 40.53 | Accuracy (%) | 28.4 |
| Open LLM Leaderboard - BBH | 15.42 | Score | 24 |
Interactive version: theaggregate.ai/model?slug=qwen2-1-5b-ita · How It Works · Data refreshed daily, snapshot 2026-09-05.