Minerva-3B-base-v1.0: benchmark results
Provider: Other.
Aggregate Rating 1219 ± 39, rank #9491 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Pinocchio Italian - Cultura | 27.81 | Accuracy (%) | 4.5 |
| Pinocchio Italian - Diritto | 27.78 | Accuracy (%) | 4.5 |
| Pinocchio Italian - Generale | 28.1 | Accuracy (%) | 4.5 |
| Pinocchio Italian - Matematica E Scienze | 26.59 | Accuracy (%) | 4.5 |
| Pinocchio Italian Leaderboard | 27.63 | Average Accuracy (%) | 4.5 |
| Open Italian LLM - MMLU-Pro (IT) | 11.21 | Accuracy (%) | 3.6 |
| Pinocchio Italian - Lingua Straniera | 28.01 | Accuracy (%) | 2.3 |
| Pinocchio Italian - Logica | 27.47 | Accuracy (%) | 2.3 |
Interactive version: theaggregate.ai/model?slug=minerva-3b-base-v1-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.