COKALL-13B-v3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1339 ± 17, rank #2292 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 61.8 | Accuracy (%) | 64.2 |
| Open Korean LLM - KorNAT-Helpful | 46.92 | Normalized accuracy (%) | 50.7 |
| Open Korean LLM - KorNAT-Harmless | 62.46 | Normalized accuracy (%) | 44.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 7.81 | Exact match, flexible extract (%) | 30.4 |
| Open Korean LLM - KorNAT-CKA | 20.41 | Normalized accuracy (%) | 29.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 29.81 | Average Score (%) | 14 |
| Open Ko-LLM Leaderboard | 29.81 | Average (%) | 13.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.19 | Normalized accuracy (%) | 6.4 |
| Open Korean LLM - Ko-IFEval | 2 | Strict accuracy, prompt/instruction mean (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=cokall-13b-v3 · How It Works · Data refreshed daily, snapshot 2026-09-19.