Llama-3-Instruct-8B-DPO Benchmark Results

Llama-3-Instruct-8B-DPO — benchmark results

Provider: Meta. Released 2024-05-17. Access: Open.

Unified ELO 1396 ± 52, rank #1246 of 1776 rated models, from 7 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM Leaderboard	533.36	Average Score (%)	90.7
Open LLM Leaderboard - IFEval	67.57	Score	80.1
Open LLM Leaderboard - MMLU-Pro	29.61	Score	57.8
Open LLM Leaderboard - BBH	28.51	Score	46.9
Open LLM Leaderboard - MATH Level 5	8.46	Score	42.5
Open LLM Leaderboard - GPQA	2.91	Score	26.7
Open LLM Leaderboard - MuSR	3.93	Score	19.3