Llama 3 4B Community: benchmark results
Provider: Meta.
Aggregate Rating 1102 ± 42, rank #10699 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.43 | MC2 (%) (0-shot) | 44.7 |
| Open LLM Leaderboard v1 - MMLU | 25.53 | Accuracy (%) (5-shot) | 8.7 |
| Open LLM Leaderboard v1 - WinoGrande | 51.46 | Accuracy (%) (5-shot) | 5.4 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 24.91 | Normalized accuracy (%) (25-shot) | 4.2 |
| Open LLM Leaderboard v1 - HellaSwag | 25.72 | Normalized accuracy (%) (10-shot) | 1.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-4b-community · How It Works · Data refreshed daily, snapshot 2026-11-08.