Llama 3 70B Instruct DPO V0.4: benchmark results
Provider: Meta.
Aggregate Rating 1535 ± 35, rank #1893 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 87.34 | Accuracy (%) (5-shot) | 100 |
| Open LLM Leaderboard v1 - MMLU | 80.5 | Accuracy (%) (5-shot) | 99.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.61 | Normalized accuracy (%) (25-shot) | 92.8 |
| Open LLM Leaderboard v1 - WinoGrande | 83.58 | Accuracy (%) (5-shot) | 89.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 63.26 | MC2 (%) (0-shot) | 80.4 |
| Open LLM Leaderboard v1 - HellaSwag | 86.03 | Normalized accuracy (%) (10-shot) | 78.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-70b-instruct-dpo-v0-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.