llama3-5.4B-instruct: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1192 ± 38, rank #9661 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.85 | MC2 (%) (0-shot) | 53.5 |
| Open LLM Leaderboard v1 - WinoGrande | 67.8 | Accuracy (%) (5-shot) | 21.7 |
| Open LLM Leaderboard v1 - MMLU | 31.16 | Accuracy (%) (5-shot) | 17 |
| Open LLM Leaderboard v1 - ARC Challenge | 39.93 | Normalized accuracy (%) (25-shot) | 16.2 |
| Open LLM Leaderboard v1 - HellaSwag | 51.27 | Normalized accuracy (%) (10-shot) | 10.6 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=llama3-5-4b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.