Llama 3 8B Usenet Merged: benchmark results
Provider: Meta.
Aggregate Rating 1402 ± 36, rank #5962 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Italian LLM - MMLU-Pro (IT) | 26.29 | Accuracy (%) | 71.4 |
| Pinocchio Italian - Diritto | 51.08 | Accuracy (%) | 59.1 |
| Pinocchio Italian - Cultura | 56.43 | Accuracy (%) | 54.5 |
| Pinocchio Italian - Generale | 53.95 | Accuracy (%) | 54.5 |
| Pinocchio Italian - Matematica E Scienze | 46.57 | Accuracy (%) | 54.5 |
| Pinocchio Italian Leaderboard | 51.47 | Average Accuracy (%) | 50 |
| Pinocchio Italian - Logica | 39.24 | Accuracy (%) | 43.2 |
| Pinocchio Italian - Lingua Straniera | 61.52 | Accuracy (%) | 38.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-usenet-merged · How It Works · Data refreshed daily, snapshot 2026-11-08.