Llama 3 8B Instruct DPO V0.3: benchmark results
Provider: MaziyarPanahi. Access: Open.
Aggregate Rating 1429 ± 35, rank #4708 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 70.58 | Accuracy (%) (5-shot) | 93.6 |
| Open LLM Leaderboard v1 - MMLU | 68.33 | Accuracy (%) (5-shot) | 91.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.29 | MC2 (%) (0-shot) | 59.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
| Open LLM Leaderboard v1 - WinoGrande | 75.37 | Accuracy (%) (5-shot) | 41.8 |
| Open LLM Leaderboard v1 - HellaSwag | 79.2 | Normalized accuracy (%) (10-shot) | 37.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-dpo-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.