Llama 3 70B Orpo V0.1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1559 ± 21, rank #839 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 76.8 | Accuracy (%) (5-shot) | 99.4 |
| Open LLM Leaderboard v1 - MMLU | 79.39 | Accuracy (%) (5-shot) | 99.4 |
| Open LLM Leaderboard v1 - WinoGrande | 85.48 | Accuracy (%) (5-shot) | 98.4 |
| Open LLM Leaderboard v1 - HellaSwag | 88.01 | Normalized accuracy (%) (10-shot) | 89.2 |
| Open LLM Leaderboard - MuSR | 45.34 | Score | 85 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.69 | Normalized accuracy (%) (25-shot) | 81.1 |
| Open LLM Leaderboard - MMLU-Pro | 38.93 | Score | 70.2 |
| Open LLM Leaderboard - MATH Level 5 | 15.79 | Score | 63.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.62 | MC2 (%) (0-shot) | 45.5 |
| Open LLM Leaderboard - BBH | 46.55 | Score | 37.6 |
| Open LLM Leaderboard - IFEval | 20.49 | Score | 12.7 |
| Open LLM Leaderboard - GPQA | 25.76 | Score | 9.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-70b-orpo-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-23.