Llama 2 7B ShareGPT Wiki Noprompt News CoT Blending Circulus Benchmark Results

Llama 2 7B ShareGPT Wiki Noprompt News CoT Blending Circulus: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1385 ± 17, rank #2015 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - KorNAT-Harmless	64.21	Normalized accuracy (%)	71.7
Open Korean LLM - Ko-IFEval	32.27	Strict accuracy, prompt/instruction mean (%)	61.9
Open Korean LLM - KorNAT-Helpful	46.42	Normalized accuracy (%)	46
Open Korean LLM - KorNAT-CKA	22.22	Normalized accuracy (%)	38.9
Open Korean LLM - Ko-GSM8K (flexible extract)	11.83	Exact match, flexible extract (%)	37.6
Open Korean LLM Leaderboard	32.45	Average Score (%)	33.7
Open Ko-LLM Leaderboard	32.46	Average (%)	33.4
Open Korean LLM - Ko-GPQA-Diamond	21.72	Normalized accuracy (%)	29.4
Open Korean LLM - Ko-Winogrande	55.33	Accuracy (%)	19.7
Open Korean LLM - Ko-EQ-Bench	-1.16	EQ-Bench score	3.9