rombos_Replete-Coder-Llama3-8B Benchmark Results

rombos_Replete-Coder-Llama3-8B — benchmark results

Provider: Other. Released 2024-10-06. Access: Open.

Unified ELO 1356 ± 12, rank #1394 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM Leaderboard	373.09	Average Score (%)	73.7
Open Chinese LLM - WinoGrande	64.33	Accuracy (%)	66.3
Open LLM Leaderboard - IFEval	47.14	Score	54.2
Open LLM Leaderboard - MuSR	7.71	Score	35.9
Open Chinese LLM - CMMLU	49.77	Accuracy (%)	32.6
Open Chinese LLM - GSM8K	32.68	Accuracy (%)	27.9
Open Chinese LLM - HellaSwag	54.65	Accuracy (%)	22.8
Open LLM Leaderboard - MATH Level 5	3.93	Score	22.6
Open Chinese LLM - TruthfulQA MC	50.45	Accuracy (%)	21.4
Open LLM Leaderboard - GPQA	2.24	Score	21.2
Open Chinese LLM Leaderboard	50.69	Average Score (%)	21.1
Open Chinese LLM - C-Eval Semantic	59.63	Accuracy (%)	20.5