COKAL-DPO-13B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1444 ± 17, rank #1558 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 71.03 | Accuracy (%) | 97.4 |
| Open Korean LLM - KorNAT-Helpful | 52.73 | Normalized accuracy (%) | 93.7 |
| Open Korean LLM - KorNAT-Harmless | 68.53 | Normalized accuracy (%) | 92.1 |
| Open Korean LLM - KorNAT-CKA | 30.19 | Normalized accuracy (%) | 82.5 |
| Open Ko-LLM Leaderboard | 37 | Average (%) | 60.3 |
| Open Korean LLM Leaderboard | 37 | Average Score (%) | 60.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 18.42 | Exact match, flexible extract (%) | 49.5 |
| Open Korean LLM - Ko-IFEval | 23.5 | Strict accuracy, prompt/instruction mean (%) | 27.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=cokal-dpo-13b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.