Mistral-7B-ko-v0.1: benchmark results

Provider: Mistral. Access: Open.

Unified ELO 1402 ± 17, rank #1893 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-GPQA-Diamond26.77Normalized accuracy (%)88.9
Open Korean LLM - KorNAT-Helpful48.62Normalized accuracy (%)70.6
Open Korean LLM - KorNAT-Harmless62.79Normalized accuracy (%)50.3
Open Korean LLM - Ko-GSM8K (flexible extract)15.09Exact match, flexible extract (%)44.4
Open Korean LLM - Ko-IFEval27.55Strict accuracy, prompt/instruction mean (%)43.8
Open Korean LLM Leaderboard33.47Average Score (%)42.1
Open Ko-LLM Leaderboard33.47Average (%)41.9
Open Korean LLM - Ko-Winogrande58.8Accuracy (%)41.4
Open Korean LLM - KorNAT-CKA16.91Normalized accuracy (%)13.8
Open Korean LLM - Ko-EQ-Bench-4.03EQ-Bench score2.7

Interactive version: theaggregate.ai/model?slug=mistral-7b-ko-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.