mistral-ko-7B-wiki-neft: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1339 ± 17, rank #2294 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 25.52 | Strict accuracy, prompt/instruction mean (%) | 35.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.46 | Exact match, flexible extract (%) | 34.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 19.07 | Normalized accuracy (%) | 22.6 |
| Open Korean LLM - Ko-Winogrande | 55.17 | Accuracy (%) | 19 |
| Open Korean LLM Leaderboard | 29.96 | Average Score (%) | 15.5 |
| Open Ko-LLM Leaderboard | 29.96 | Average (%) | 15.4 |
| Open Korean LLM - KorNAT-Harmless | 60.47 | Normalized accuracy (%) | 15 |
| Open Korean LLM - KorNAT-Helpful | 41 | Normalized accuracy (%) | 9.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 17.68 | Normalized accuracy (%) | 1.3 |
Interactive version: theaggregate.ai/model?slug=mistral-ko-7b-wiki-neft · How It Works · Data refreshed daily, snapshot 2026-09-19.