Llama 2 7B Dpo V1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1369 ± 17, rank #2116 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - KorNAT-Harmless | 63.22 | Normalized accuracy (%) | 58.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.9 | Exact match, flexible extract (%) | 29 |
| Open Korean LLM Leaderboard | 31.48 | Average Score (%) | 27.7 |
| Open Ko-LLM Leaderboard | 31.48 | Average (%) | 27.5 |
| Open Korean LLM - KorNAT-CKA | 19.64 | Normalized accuracy (%) | 25.8 |
| Open Korean LLM - Ko-Winogrande | 56.12 | Accuracy (%) | 24.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 43.2 | Normalized accuracy (%) | 22.1 |
| Open Korean LLM - Ko-IFEval | 19.88 | Strict accuracy, prompt/instruction mean (%) | 17.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-dpo-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.