mistrallite.kor: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1335 ± 17, rank #2319 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 47.8 | Normalized accuracy (%) | 60.8 |
| Open Korean LLM - Ko-IFEval | 24.65 | Strict accuracy, prompt/instruction mean (%) | 30.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.64 | Accuracy (%) | 21.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 3.26 | Exact match, flexible extract (%) | 21.3 |
| Open Korean LLM Leaderboard | 29.91 | Average Score (%) | 15.3 |
| Open Ko-LLM Leaderboard | 29.91 | Average (%) | 15.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - KorNAT-Harmless | 59.83 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - KorNAT-CKA | 11.85 | Normalized accuracy (%) | 2.8 |
Interactive version: theaggregate.ai/model?slug=mistrallite-kor · How It Works · Data refreshed daily, snapshot 2026-09-19.