LLaMA2-ko-7B-KNUT-v0.1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1372 ± 17, rank #2102 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-CKA | 21.3 | Normalized accuracy (%) | 34 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 7.96 | Exact match, flexible extract (%) | 30.7 |
| Open Korean LLM - Ko-IFEval | 24.26 | Strict accuracy, prompt/instruction mean (%) | 29.6 |
| Open Korean LLM Leaderboard | 31.76 | Average Score (%) | 29.3 |
| Open Ko-LLM Leaderboard | 31.76 | Average (%) | 29.1 |
| Open Korean LLM - Ko-Winogrande | 56.91 | Accuracy (%) | 28.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 41.05 | Normalized accuracy (%) | 9.9 |
| Open Korean LLM - KorNAT-Harmless | 58.63 | Normalized accuracy (%) | 3.7 |
Interactive version: theaggregate.ai/model?slug=llama2-ko-7b-knut-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.