kullama2-7B-ko-PGO: benchmark results
Provider: Other. Access: Open.
Unified ELO 1330 ± 17, rank #2348 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 48.5 | Normalized accuracy (%) | 69.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-Winogrande | 58.41 | Accuracy (%) | 38.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.14 | Exact match, flexible extract (%) | 27.1 |
| Open Korean LLM - KorNAT-CKA | 19.62 | Normalized accuracy (%) | 25.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.12 | Normalized accuracy (%) | 11.9 |
| Open Korean LLM Leaderboard | 29.34 | Average Score (%) | 11.2 |
| Open Ko-LLM Leaderboard | 29.34 | Average (%) | 11 |
| Open Korean LLM - Ko-IFEval | 0.18 | Strict accuracy, prompt/instruction mean (%) | 1.5 |
Interactive version: theaggregate.ai/model?slug=kullama2-7b-ko-pgo · How It Works · Data refreshed daily, snapshot 2026-09-19.