COLA3_13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1366 ± 17, rank #2132 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 67.09 | Accuracy (%) | 90.5 |
| Open Korean LLM - KorNAT-CKA | 23.83 | Normalized accuracy (%) | 47.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.7 | Exact match, flexible extract (%) | 33.1 |
| Open Korean LLM - KorNAT-Harmless | 61.62 | Normalized accuracy (%) | 31.8 |
| Open Korean LLM Leaderboard | 31.11 | Average Score (%) | 25.1 |
| Open Ko-LLM Leaderboard | 31.11 | Average (%) | 24.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - KorNAT-Helpful | 42.48 | Normalized accuracy (%) | 16.8 |
| Open Korean LLM - Ko-IFEval | 7.91 | Strict accuracy, prompt/instruction mean (%) | 7 |
Interactive version: theaggregate.ai/model?slug=cola3-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.