Llama 3 6B V0.1: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1355 ± 40, rank #7568 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 61.84 | Accuracy (%) (5-shot) | 53 |
| Open LLM Leaderboard v1 - GSM8K | 24.11 | Accuracy (%) (5-shot) | 43.4 |
| Open LLM Leaderboard v1 - WinoGrande | 73.01 | Accuracy (%) (5-shot) | 30.7 |
| Open LLM Leaderboard v1 - HellaSwag | 74.67 | Normalized accuracy (%) (10-shot) | 25.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 48.21 | Normalized accuracy (%) (25-shot) | 23 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43 | MC2 (%) (0-shot) | 22.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-6b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.