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

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

Provider: Meta. Released 2024-07-06. Access: Open.

Unified ELO 1375 ± 80, rank #1328 of 1776 rated models, from 7 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	72.75	Score	86.7
Open Korean LLM Leaderboard	482	Average Score (%)	85.5
Open LLM Leaderboard - MMLU-Pro	29.37	Score	56.6
Open LLM Leaderboard - MATH Level 5	9.67	Score	46.2
Open LLM Leaderboard - BBH	27.22	Score	43.2
Open LLM Leaderboard - GPQA	4.03	Score	35.2
Open LLM Leaderboard - MuSR	1.48	Score	5.9