COKALL-13B-v4: benchmark results
Provider: Other. Access: Open.
Unified ELO 1347 ± 17, rank #2254 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 62.43 | Accuracy (%) | 68.5 |
| Open Korean LLM - KorNAT-Helpful | 47.38 | Normalized accuracy (%) | 56 |
| Open Korean LLM - KorNAT-Harmless | 62.56 | Normalized accuracy (%) | 46.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.17 | Exact match, flexible extract (%) | 32.3 |
| Open Korean LLM - KorNAT-CKA | 19.77 | Normalized accuracy (%) | 26.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 30.12 | Average Score (%) | 17.1 |
| Open Ko-LLM Leaderboard | 30.12 | Average (%) | 17 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.19 | Normalized accuracy (%) | 6.4 |
| Open Korean LLM - Ko-IFEval | 2.75 | Strict accuracy, prompt/instruction mean (%) | 4.5 |
Interactive version: theaggregate.ai/model?slug=cokall-13b-v4 · How It Works · Data refreshed daily, snapshot 2026-09-19.