Llama-3-Base-8B-SFT-SimPO Benchmark Results

Llama-3-Base-8B-SFT-SimPO — benchmark results

Provider: Meta. Released 2024-05-24. Access: Open.

Unified ELO 1368 ± 39, rank #1353 of 1776 rated models, from 7 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	11.85	Score	63.8
Open LLM Leaderboard - IFEval	46.85	Score	53.5
Open Korean LLM Leaderboard	94.64	Average Score (%)	50.5
Open LLM Leaderboard - GPQA	5.15	Score	43.2
Open LLM Leaderboard - BBH	26.4	Score	41.3
Open LLM Leaderboard - MMLU-Pro	23.39	Score	40.2
Open LLM Leaderboard - MATH Level 5	5.51	Score	30.6