COKA-DPO-test-v1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1376 ± 17, rank #2083 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.15 | Normalized accuracy (%) | 77 |
| Open Korean LLM - Ko-Winogrande | 61.48 | Accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Harmless | 63.25 | Normalized accuracy (%) | 59 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.78 | Exact match, flexible extract (%) | 43.6 |
| Open Korean LLM - KorNAT-CKA | 20.79 | Normalized accuracy (%) | 31.5 |
| Open Korean LLM Leaderboard | 31.83 | Average Score (%) | 29.5 |
| Open Ko-LLM Leaderboard | 31.83 | Average (%) | 29.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 14.98 | Strict accuracy, prompt/instruction mean (%) | 10.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.18 | Normalized accuracy (%) | 2.3 |
Interactive version: theaggregate.ai/model?slug=coka-dpo-test-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.