llama3-pre1-pre2-inst3-lora3-mergkit-base Benchmark Results

llama3-pre1-pre2-inst3-lora3-mergkit-base: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1318 ± 17, rank #2399 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	21.72	Normalized accuracy (%)	29.4
Open Korean LLM - KorNAT-CKA	20.14	Normalized accuracy (%)	28.5
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-IFEval	22.53	Strict accuracy, prompt/instruction mean (%)	23.8
Open Korean LLM - Ko-GSM8K (flexible extract)	1.82	Exact match, flexible extract (%)	16.1
Open Korean LLM Leaderboard	29.26	Average Score (%)	10.6
Open Ko-LLM Leaderboard	29.26	Average (%)	10.5
Open Korean LLM - KorNAT-Harmless	59.6	Normalized accuracy (%)	7.7
Open Korean LLM - KorNAT-Helpful	38.17	Normalized accuracy (%)	3.2
Open Korean LLM - Ko-Winogrande	49.72	Accuracy (%)	2