Llama-3-COT-ITA: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1425 ± 36, rank #4919 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Italian LLM - MMLU-Pro (IT) | 29.13 | Accuracy (%) | 78.6 |
| Pinocchio Italian - Matematica E Scienze | 48.79 | Accuracy (%) | 65.9 |
| Pinocchio Italian - Diritto | 54.42 | Accuracy (%) | 63.6 |
| Pinocchio Italian - Cultura | 58.93 | Accuracy (%) | 61.4 |
| Pinocchio Italian - Generale | 57.07 | Accuracy (%) | 61.4 |
| Pinocchio Italian - Logica | 42.66 | Accuracy (%) | 61.4 |
| Pinocchio Italian Leaderboard | 54.69 | Average Accuracy (%) | 59.1 |
| Pinocchio Italian - Lingua Straniera | 66.24 | Accuracy (%) | 45.5 |
Interactive version: theaggregate.ai/model?slug=llama-3-cot-ita · How It Works · Data refreshed daily, snapshot 2026-11-08.