Mistral-7B-KNUT-ref: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1362 ± 17, rank #2159 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-EQ-Bench | 1.23 | EQ-Bench score | 46.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.61 | Exact match, flexible extract (%) | 34.6 |
| Open Korean LLM - KorNAT-Helpful | 43.9 | Normalized accuracy (%) | 26.4 |
| Open Korean LLM - Ko-IFEval | 23.29 | Strict accuracy, prompt/instruction mean (%) | 26.1 |
| Open Ko-LLM Leaderboard | 30.96 | Average (%) | 23.6 |
| Open Korean LLM Leaderboard | 30.96 | Average Score (%) | 23.5 |
| Open Korean LLM - KorNAT-CKA | 19.16 | Normalized accuracy (%) | 23.2 |
| Open Korean LLM - KorNAT-Harmless | 61.02 | Normalized accuracy (%) | 22 |
| Open Korean LLM - Ko-Winogrande | 55.17 | Accuracy (%) | 19 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-knut-ref · How It Works · Data refreshed daily, snapshot 2026-09-19.