Llama-3-Instruct-8B-DPO-v0.2 Benchmark Results

Llama-3-Instruct-8B-DPO-v0.2 — benchmark results

Princeton NLP's DPO v0.2 baseline on Llama 3 8B Instruct, released with the SimPO paper's updated baseline suite. Provider: Meta. Released 2024-07-06. Access: Open.

Unified ELO 1426 ± 42, rank #1104 of 1776 rated models, from 7 benchmark results.

Strongest benchmark results

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	72.08	Score	85.9
Open Korean LLM Leaderboard	431.34	Average Score (%)	80.6
Open LLM Leaderboard - MMLU-Pro	30.77	Score	63.6
Open LLM Leaderboard - BBH	28.94	Score	48.2
Open LLM Leaderboard - MATH Level 5	8.99	Score	44.2
Open LLM Leaderboard - GPQA	4.92	Score	41.7
Open LLM Leaderboard - MuSR	5.56	Score	27

Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-dpo-v0-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.