ko-en-llama2-13B-finetune: benchmark results
Provider: Other. Access: Open.
Unified ELO 1373 ± 17, rank #2101 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.22 | Accuracy (%) | 87.8 |
| Open Korean LLM - KorNAT-Harmless | 63.42 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Helpful | 46.42 | Normalized accuracy (%) | 46 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.03 | Exact match, flexible extract (%) | 42.3 |
| Open Korean LLM Leaderboard | 31.57 | Average Score (%) | 28.2 |
| Open Ko-LLM Leaderboard | 31.57 | Average (%) | 27.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 19.11 | Normalized accuracy (%) | 22.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - Ko-IFEval | 10.09 | Strict accuracy, prompt/instruction mean (%) | 8 |
Interactive version: theaggregate.ai/model?slug=ko-en-llama2-13b-finetune · How It Works · Data refreshed daily, snapshot 2026-09-19.