COKAL_pre_DPO_Test_v2-13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1385 ± 17, rank #2017 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.1 | Normalized accuracy (%) | 76.5 |
| Open Korean LLM - Ko-Winogrande | 63.14 | Accuracy (%) | 72.6 |
| Open Korean LLM - KorNAT-Harmless | 63.45 | Normalized accuracy (%) | 62.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.63 | Exact match, flexible extract (%) | 43.3 |
| Open Korean LLM Leaderboard | 32.4 | Average Score (%) | 33.2 |
| Open Ko-LLM Leaderboard | 32.4 | Average (%) | 32.8 |
| Open Korean LLM - KorNAT-CKA | 20.84 | Normalized accuracy (%) | 31.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 17.14 | Strict accuracy, prompt/instruction mean (%) | 12.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.69 | Normalized accuracy (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=cokal-pre-dpo-test-v2-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.