COKALL-13B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1335 ± 17, rank #2320 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 62.04 | Accuracy (%) | 65.8 |
| Open Korean LLM - KorNAT-Helpful | 46.83 | Normalized accuracy (%) | 49.7 |
| Open Korean LLM - KorNAT-Harmless | 62.37 | Normalized accuracy (%) | 42.8 |
| Open Korean LLM - KorNAT-CKA | 20.57 | Normalized accuracy (%) | 30.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.82 | Exact match, flexible extract (%) | 28.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 29.64 | Average Score (%) | 12.7 |
| Open Ko-LLM Leaderboard | 29.64 | Average (%) | 12.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.19 | Normalized accuracy (%) | 6.4 |
| Open Korean LLM - Ko-IFEval | 1.5 | Strict accuracy, prompt/instruction mean (%) | 3.5 |
Interactive version: theaggregate.ai/model?slug=cokall-13b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.