Llama-3-Petro-Instruct-v1 (Publisher: FelixChao): benchmark results
Provider: Meta.
Aggregate Rating 1392 ± 36, rank #6470 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 57.47 | Accuracy (%) (5-shot) | 69.2 |
| Open LLM Leaderboard v1 - MMLU | 64 | Accuracy (%) (5-shot) | 64.7 |
| Open LLM Leaderboard v1 - WinoGrande | 74.51 | Accuracy (%) (5-shot) | 37 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.66 | Normalized accuracy (%) (25-shot) | 35.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.43 | MC2 (%) (0-shot) | 34.4 |
| Open LLM Leaderboard v1 - HellaSwag | 76.56 | Normalized accuracy (%) (10-shot) | 28.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-petro-instruct-v1-publisher-felixchao · How It Works · Data refreshed daily, snapshot 2026-11-08.