Llama-3-8B-Lexi-Uncensored: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1418 ± 36, rank #5288 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.68 | Accuracy (%) (5-shot) | 89.7 |
| Open LLM Leaderboard v1 - GSM8K | 68.39 | Accuracy (%) (5-shot) | 85.8 |
| Open LLM Leaderboard v1 - WinoGrande | 75.85 | Accuracy (%) (5-shot) | 44.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.56 | Normalized accuracy (%) (25-shot) | 43.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.72 | MC2 (%) (0-shot) | 38.5 |
| Open LLM Leaderboard v1 - HellaSwag | 77.88 | Normalized accuracy (%) (10-shot) | 32.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-lexi-uncensored · How It Works · Data refreshed daily, snapshot 2026-11-08.