GenAI-llama2-ko-en-dpo-13B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1387 ± 17, rank #2003 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 50.9 | Normalized accuracy (%) | 87.9 |
| Open Korean LLM - Ko-Winogrande | 64.09 | Accuracy (%) | 77.1 |
| Open Korean LLM - KorNAT-Harmless | 63.73 | Normalized accuracy (%) | 66 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.94 | Exact match, flexible extract (%) | 43.9 |
| Open Korean LLM Leaderboard | 32.63 | Average Score (%) | 35 |
| Open Ko-LLM Leaderboard | 32.63 | Average (%) | 34.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 18.92 | Normalized accuracy (%) | 21.2 |
| Open Korean LLM - Ko-IFEval | 14.02 | Strict accuracy, prompt/instruction mean (%) | 9.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 16.67 | Normalized accuracy (%) | 0.4 |
Interactive version: theaggregate.ai/model?slug=genai-llama2-ko-en-dpo-13b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.