COLA3-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1306 ± 18, rank #2439 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-CKA | 22.12 | Normalized accuracy (%) | 38.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.07 | Exact match, flexible extract (%) | 26.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.64 | Accuracy (%) | 21.5 |
| Open Korean LLM - KorNAT-Helpful | 41.58 | Normalized accuracy (%) | 12.8 |
| Open Korean LLM - KorNAT-Harmless | 59.74 | Normalized accuracy (%) | 8.8 |
| Open Ko-LLM Leaderboard | 28.17 | Average (%) | 5.2 |
| Open Korean LLM Leaderboard | 28.17 | Average Score (%) | 5.2 |
| Open Korean LLM - Ko-IFEval | 0.18 | Strict accuracy, prompt/instruction mean (%) | 1.5 |
Interactive version: theaggregate.ai/model?slug=cola3-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.