Llama 2 7B KoNqa Test V1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1359 ± 18, rank #2180 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 59.35 | Accuracy (%) | 45.5 |
| Open Korean LLM - Ko-IFEval | 26.09 | Strict accuracy, prompt/instruction mean (%) | 38 |
| Open Korean LLM - KorNAT-CKA | 20.74 | Normalized accuracy (%) | 31.1 |
| Open Korean LLM Leaderboard | 31.17 | Average Score (%) | 25.9 |
| Open Ko-LLM Leaderboard | 31.17 | Average (%) | 25.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.27 | Exact match, flexible extract (%) | 18.5 |
| Open Korean LLM - KorNAT-Helpful | 42.75 | Normalized accuracy (%) | 18.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - KorNAT-Harmless | 59.67 | Normalized accuracy (%) | 8.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-konqa-test-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.