CodeNinja-1.0-OpenChat-7B Benchmark Results

CodeNinja-1.0-OpenChat-7B — benchmark results

Provider: Other. Released 2023-12-20. Access: Open.

Unified ELO 1375 ± 15, rank #1326 of 1776 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	54.47	Score	65.6
Open Korean LLM Leaderboard	272.61	Average Score (%)	65
Open LLM Leaderboard - MuSR	11.54	Score	61.3
Open LLM Leaderboard - GPQA	5.93	Score	49.7
Open Chinese LLM - TruthfulQA MC	52.75	Accuracy (%)	39.8
Open LLM Leaderboard - MMLU-Pro	22.39	Score	36.9
Open LLM Leaderboard - MATH Level 5	6.72	Score	36.4
Open LLM Leaderboard - BBH	21.71	Score	32.4
Open Chinese LLM - GSM8K	35.48	Accuracy (%)	31.3
Open Chinese LLM - CMMLU	45.88	Accuracy (%)	14.8
Open Chinese LLM Leaderboard	48.7	Average Score (%)	14.8
Open Chinese LLM - ARC Challenge	44.28	Accuracy (%)	14.1