Mistral-Nemo-Instruct-2407_sft_ver_4.4: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1479 ± 18, rank #1296 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 68.35 | Accuracy (%) | 93 |
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 49.51 | Exact match, flexible extract (%) | 83.1 |
| Open Korean LLM - Ko-IFEval | 38.77 | Strict accuracy, prompt/instruction mean (%) | 80.3 |
| Open Korean LLM - Ko-EQ-Bench | 26.08 | EQ-Bench score | 72.7 |
| Open Korean LLM Leaderboard | 39.39 | Average Score (%) | 72.1 |
| Open Ko-LLM Leaderboard | 39.39 | Average (%) | 71.8 |
| Open Korean LLM - KorNAT-CKA | 25.4 | Normalized accuracy (%) | 57.9 |
| Open Korean LLM - KorNAT-Harmless | 63.07 | Normalized accuracy (%) | 54.9 |
| Open Korean LLM - KorNAT-Helpful | 46.8 | Normalized accuracy (%) | 49.4 |
Interactive version: theaggregate.ai/model?slug=mistral-nemo-instruct-2407-sft-ver-4-4 · How It Works · Data refreshed daily, snapshot 2026-09-19.