LLaMAntino-2-chat-13B-hf-UltraChat-ITA: benchmark results
Provider: Meta.
Aggregate Rating 1338 ± 37, rank #8000 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Italian LLM - MMLU-Pro (IT) | 20.66 | Accuracy (%) | 35.7 |
| Pinocchio Italian - Diritto | 42.85 | Accuracy (%) | 25 |
| Pinocchio Italian - Lingua Straniera | 48.13 | Accuracy (%) | 25 |
| Pinocchio Italian - Generale | 45.05 | Accuracy (%) | 20.5 |
| Pinocchio Italian - Cultura | 45.45 | Accuracy (%) | 19.3 |
| Pinocchio Italian Leaderboard | 42.43 | Average Accuracy (%) | 18.2 |
| Pinocchio Italian - Logica | 35.09 | Accuracy (%) | 15.9 |
| Pinocchio Italian - Matematica E Scienze | 38.02 | Accuracy (%) | 15.9 |
Interactive version: theaggregate.ai/model?slug=llamantino-2-chat-13b-hf-ultrachat-ita · How It Works · Data refreshed daily, snapshot 2026-11-08.