lion-llama3-8B [4bit]: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1389 ± 33, rank #6569 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 77.51 | Accuracy (%) (5-shot) | 56.4 |
| Open LLM Leaderboard v1 - MMLU | 62.44 | Accuracy (%) (5-shot) | 55.3 |
| Open LLM Leaderboard v1 - GSM8K | 37.91 | Accuracy (%) (5-shot) | 53 |
| Open LLM Leaderboard v1 - HellaSwag | 80.42 | Normalized accuracy (%) (10-shot) | 40.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.19 | Normalized accuracy (%) (25-shot) | 39.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.97 | MC2 (%) (0-shot) | 19 |
Interactive version: theaggregate.ai/model?slug=lion-llama3-8b-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.