Llama 3 8B Ita: benchmark results
DeepMount00's Italian-language fine-tune of Meta's Llama 3 8B, optimized for Italian conversation and text generation. Provider: DeepMount00. Released 2024-04-18. Access: Open.
Aggregate Rating 1462 ± 13, rank #926 of 1656 rated models, from 65 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - PubMedQA | 78.4 | Accuracy (%) | 97.1 |
| Open LLM Leaderboard v1 - HellaSwag | 89.08 | Normalized accuracy (%) (10-shot) | 96.8 |
| Open Italian LLM - MMLU-Pro (IT) | 30.7 | Accuracy (%) | 96.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.95 | Normalized accuracy (%) (25-shot) | 94.5 |
| Open Korean LLM - KorNAT-Helpful | 52.95 | Normalized accuracy (%) | 93.9 |
| Open Korean LLM - Ko-EQ-Bench | 39.88 | EQ-Bench score | 91.4 |
| Open LLM Leaderboard - IFEval | 75.3 | Score | 90.7 |
| Open LLM Leaderboard v1 - MMLU | 68.08 | Accuracy (%) (5-shot) | 90.5 |
| Open Korean LLM - Ko-IFEval | 45.59 | Strict accuracy, prompt/instruction mean (%) | 90 |
| Open Medical LLM - MMLU College Biology | 80.56 | Accuracy (%) | 87.5 |
| Open Korean LLM Leaderboard | 43.01 | Average Score (%) | 87.3 |
| Open Ko-LLM Leaderboard | 43.01 | Average (%) | 87.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-ita · How It Works · Data refreshed daily, snapshot 2026-10-20.