Llama 3 8B Instruct V0.3: benchmark results
Provider: MaziyarPanahi. Access: Open.
Aggregate Rating 1428 ± 35, rank #4764 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 69.98 | Accuracy (%) (5-shot) | 91.1 |
| Open LLM Leaderboard v1 - MMLU | 68.13 | Accuracy (%) (5-shot) | 90.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.77 | MC2 (%) (0-shot) | 60.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.37 | Normalized accuracy (%) (25-shot) | 57.6 |
| Open LLM Leaderboard v1 - WinoGrande | 75.53 | Accuracy (%) (5-shot) | 42.7 |
| Open LLM Leaderboard v1 - HellaSwag | 79.55 | Normalized accuracy (%) (10-shot) | 38.3 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.