komt-mistral-7B-v1-dpo-osy-v1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1393 ± 17, rank #1961 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 35.92 | Strict accuracy, prompt/instruction mean (%) | 74.3 |
| Open Korean LLM - KorNAT-Harmless | 64.25 | Normalized accuracy (%) | 71.9 |
| Open Korean LLM - KorNAT-CKA | 25.62 | Normalized accuracy (%) | 59.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 19.41 | Exact match, flexible extract (%) | 50.7 |
| Open Korean LLM Leaderboard | 32.93 | Average Score (%) | 36.7 |
| Open Ko-LLM Leaderboard | 32.93 | Average (%) | 36.4 |
| Open Korean LLM - KorNAT-Helpful | 44.35 | Normalized accuracy (%) | 29.1 |
| Open Korean LLM - Ko-Winogrande | 56.59 | Accuracy (%) | 27.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - Ko-EQ-Bench | -1.95 | EQ-Bench score | 3.4 |
Interactive version: theaggregate.ai/model?slug=komt-mistral-7b-v1-dpo-osy-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.