Llama-3-Instruct-8B-ORPO-v0.2: benchmark results
Princeton NLP's ORPO preference-tuned Llama 3 8B Instruct, released as a baseline from the SimPO paper. Provider: Meta. Released 2024-07-06. Access: Open.
Unified ELO 1526 ± 1, rank #633 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 76.33 | Score | 92 |
| Open Korean LLM Leaderboard | 43.18 | Average Score (%) | 85.7 |
| Open LLM Leaderboard - MMLU-Pro | 30.34 | Score | 61.5 |
| Open LLM Leaderboard - BBH | 29.6 | Score | 50.2 |
| Open LLM Leaderboard - MATH Level 5 | 10.2 | Score | 48 |
| Open LLM Leaderboard - GPQA | 4.47 | Score | 38.5 |
| Open LLM Leaderboard - MuSR | 4.85 | Score | 23.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-orpo-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-08.