Llama 2 13B Dpo Test V0.2: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1352 ± 18, rank #2223 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 72.97 | Normalized accuracy (%) | 96 |
| Open Korean LLM - KorNAT-Helpful | 49.02 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-Winogrande | 61.8 | Accuracy (%) | 64.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Ko-LLM Leaderboard | 30.89 | Average (%) | 22.6 |
| Open Korean LLM Leaderboard | 30.89 | Average Score (%) | 22.6 |
| Open Korean LLM - Ko-IFEval | 18.58 | Strict accuracy, prompt/instruction mean (%) | 14 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.18 | Normalized accuracy (%) | 2.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
| Open Korean LLM - KorNAT-CKA | 6.47 | Normalized accuracy (%) | 0.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-dpo-test-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.