Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge Benchmark Results

Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge — benchmark results

Provider: Meta. Released 2024-06-28. Access: Open.

Unified ELO 1398 ± 22, rank #1237 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM Leaderboard	446.82	Average Score (%)	82.1
Open LLM Leaderboard - IFEval	68.06	Score	80.7
Open Chinese LLM - TruthfulQA MC	56.24	Accuracy (%)	67.4
Open Chinese LLM - GSM8K	49.81	Accuracy (%)	66.5
Open LLM Leaderboard - MMLU-Pro	29.83	Score	59.2
Open Chinese LLM - C-Eval Semantic	69.64	Accuracy (%)	50.7
Open Chinese LLM Leaderboard	56.64	Average Score (%)	50.4
Open LLM Leaderboard - BBH	29.07	Score	48.6
Open Chinese LLM - CMMLU	52.97	Accuracy (%)	45.7
Open LLM Leaderboard - MATH Level 5	8.91	Score	43.9
Open Chinese LLM - ARC Challenge	50.6	Accuracy (%)	43
Open LLM Leaderboard - MuSR	6.7	Score	31.8