Mistral-7B-v0.1-OKI-v20231124-1e-5: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1394 ± 17, rank #1953 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 48.2 | Normalized accuracy (%) | 65.5 |
| Open Korean LLM - KorNAT-Harmless | 63.3 | Normalized accuracy (%) | 59.8 |
| Open Korean LLM - Ko-IFEval | 28.46 | Strict accuracy, prompt/instruction mean (%) | 47.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.56 | Exact match, flexible extract (%) | 43.1 |
| Open Korean LLM Leaderboard | 33.24 | Average Score (%) | 40 |
| Open Ko-LLM Leaderboard | 33.24 | Average (%) | 39.7 |
| Open Korean LLM - Ko-Winogrande | 58.09 | Accuracy (%) | 36.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - KorNAT-CKA | 15.73 | Normalized accuracy (%) | 10.5 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-v0-1-oki-v20231124-1e-5 · How It Works · Data refreshed daily, snapshot 2026-09-19.