Unsafe-Llama-3-8B: benchmark results
Provider: vicgalle. Access: Open.
Aggregate Rating 1423 ± 34, rank #5041 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.05 | Accuracy (%) (5-shot) | 88.8 |
| Open LLM Leaderboard v1 - GSM8K | 68.16 | Accuracy (%) (5-shot) | 85.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.52 | MC2 (%) (0-shot) | 52.2 |
| Open LLM Leaderboard v1 - WinoGrande | 75.53 | Accuracy (%) (5-shot) | 42.7 |
| Open LLM Leaderboard v1 - HellaSwag | 79.73 | Normalized accuracy (%) (10-shot) | 38.9 |
Interactive version: theaggregate.ai/model?slug=unsafe-llama-3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.