mistral-ko-tech-science-v1: benchmark results

Provider: Mistral. Access: Open.

Unified ELO 1401 ± 17, rank #1902 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-IFEval34.92Strict accuracy, prompt/instruction mean (%)71.7
Open Korean LLM - Ko-GSM8K (flexible extract)19.71Exact match, flexible extract (%)51.2
Open Korean LLM - Ko-Winogrande59.27Accuracy (%)45
Open Korean LLM Leaderboard33.71Average Score (%)43.7
Open Ko-LLM Leaderboard33.71Average (%)43.4
Open Korean LLM - KorNAT-Helpful44.4Normalized accuracy (%)29.5
Open Korean LLM - Ko-EQ-Bench0EQ-Bench score24.5
Open Korean LLM - Ko-GPQA-Diamond21.21Normalized accuracy (%)24
Open Korean LLM - KorNAT-Harmless60.93Normalized accuracy (%)20.8
Open Korean LLM - KorNAT-CKA15.86Normalized accuracy (%)11

Interactive version: theaggregate.ai/model?slug=mistral-ko-tech-science-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.