Llama 2 7B Ko Orcapus Test V1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1356 ± 17, rank #2194 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 25.7 | Strict accuracy, prompt/instruction mean (%) | 36.5 |
| Open Korean LLM - Ko-Winogrande | 57.93 | Accuracy (%) | 35.4 |
| Open Korean LLM - KorNAT-CKA | 20.14 | Normalized accuracy (%) | 28.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 31.06 | Average Score (%) | 24.5 |
| Open Ko-LLM Leaderboard | 31.06 | Average (%) | 24.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.35 | Exact match, flexible extract (%) | 18.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
| Open Korean LLM - KorNAT-Helpful | 42.4 | Normalized accuracy (%) | 15.8 |
| Open Korean LLM - KorNAT-Harmless | 59.82 | Normalized accuracy (%) | 9.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-ko-orcapus-test-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.