Llama 3 70B Instruct DPO V0.1: benchmark results
Provider: Meta.
Aggregate Rating 1528 ± 36, rank #1975 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 86.05 | Accuracy (%) (5-shot) | 99.9 |
| Open LLM Leaderboard v1 - MMLU | 80.12 | Accuracy (%) (5-shot) | 99.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.67 | Normalized accuracy (%) (25-shot) | 89.9 |
| Open LLM Leaderboard v1 - WinoGrande | 82.87 | Accuracy (%) (5-shot) | 86 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 62.11 | MC2 (%) (0-shot) | 78.6 |
| Open LLM Leaderboard v1 - HellaSwag | 85.83 | Normalized accuracy (%) (10-shot) | 77 |
Interactive version: theaggregate.ai/model?slug=llama-3-70b-instruct-dpo-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.