OrpoLlama-3-8B: benchmark results
Provider: mlabonne. Released 2024-04-18. Access: Open.
Aggregate Rating 1396 ± 27, rank #6290 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.76 | Accuracy (%) (5-shot) | 85.3 |
| Open LLM Leaderboard v1 - WinoGrande | 78.3 | Accuracy (%) (5-shot) | 62 |
| Open LLM Leaderboard v1 - GSM8K | 45.94 | Accuracy (%) (5-shot) | 59.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.4 | MC2 (%) (0-shot) | 55.7 |
| Open LLM Leaderboard v1 - HellaSwag | 82.41 | Normalized accuracy (%) (10-shot) | 51 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.13 | Normalized accuracy (%) (25-shot) | 42.2 |
| Open LLM Leaderboard - IFEval | 36.53 | Score | 34.9 |
| Open LLM Leaderboard - GPQA | 27.94 | Score | 34.2 |
| Open LLM Leaderboard - BBH | 44.24 | Score | 32.2 |
| Open LLM Leaderboard - MATH Level 5 | 5.59 | Score | 30.8 |
| Open LLM Leaderboard - MMLU-Pro | 27.05 | Score | 28.7 |
| YALL Nous Leaderboard | 47.37 | Average | 20.9 |
Interactive version: theaggregate.ai/model?slug=orpollama-3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.