Llama-3-Refueled [float16] [rev: ff6d1c3ba37B]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1403 ± 37, rank #5915 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 64.73 | Accuracy (%) (5-shot) | 75.6 |
| Open LLM Leaderboard v1 - GSM8K | 61.49 | Accuracy (%) (5-shot) | 74.2 |
| Open LLM Leaderboard v1 - WinoGrande | 80.11 | Accuracy (%) (5-shot) | 72.4 |
| Open LLM Leaderboard v1 - HellaSwag | 79.04 | Normalized accuracy (%) (10-shot) | 36.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 54.61 | Normalized accuracy (%) (25-shot) | 31.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.77 | MC2 (%) (0-shot) | 18.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-refueled-float16-rev-ff6d1c3ba37b · How It Works · Data refreshed daily, snapshot 2026-11-08.