Mistral-7B-v0.2-ko-Y24_v2.0: benchmark results

Provider: Mistral. Access: Open.

Unified ELO 1347 ± 17, rank #2253 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-GSM8K (flexible extract)19.86Exact match, flexible extract (%)51.5
Open Korean LLM - Ko-IFEval29.11Strict accuracy, prompt/instruction mean (%)50.4
Open Korean LLM - KorNAT-Harmless62.6Normalized accuracy (%)46.9
Open Korean LLM - Ko-Winogrande59.35Accuracy (%)45.5
Open Korean LLM - KorNAT-Helpful43.15Normalized accuracy (%)21.6
Open Korean LLM - KorNAT-CKA18.29Normalized accuracy (%)18.8
Open Korean LLM Leaderboard30.08Average Score (%)17
Open Ko-LLM Leaderboard30.08Average (%)16.9
Open Korean LLM - Ko-GPQA-Diamond19.7Normalized accuracy (%)9.6
Open Korean LLM - Ko-EQ-Bench-14.07EQ-Bench score1.6

Interactive version: theaggregate.ai/model?slug=mistral-7b-v0-2-ko-y24-v2-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.