mistral-ko-llm Benchmark Results

mistral-ko-llm: benchmark results

Provider: Mistral. Access: Open.

Unified ELO 1227 ± 19, rank #2605 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	27.27	Normalized accuracy (%)	92.4
Open Korean LLM - KorNAT-Harmless	62.98	Normalized accuracy (%)	52.9
Open Korean LLM - KorNAT-CKA	24.58	Normalized accuracy (%)	52.2
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-Winogrande	51.07	Accuracy (%)	5.3
Open Korean LLM - Ko-GSM8K (flexible extract)	0	Exact match, flexible extract (%)	2
Open Ko-LLM Leaderboard	25.18	Average (%)	0.3
Open Korean LLM - Ko-IFEval	0	Strict accuracy, prompt/instruction mean (%)	0.3
Open Korean LLM Leaderboard	25.18	Average Score (%)	0.3
Open Korean LLM - KorNAT-Helpful	31.32	Normalized accuracy (%)	0.2

Interactive version: theaggregate.ai/model?slug=mistral-ko-llm · How It Works · Data refreshed daily, snapshot 2026-09-19.