Ko-Qwen2-7B-Instruct: benchmark results
Provider: Other. Access: Open.
Unified ELO 1529 ± 17, rank #941 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 47.86 | EQ-Bench score | 94.6 |
| Open Korean LLM Leaderboard | 44.92 | Average Score (%) | 91.2 |
| Open Ko-LLM Leaderboard | 44.92 | Average (%) | 91.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 55.19 | Exact match, flexible extract (%) | 89.2 |
| Open Korean LLM - KorNAT-CKA | 29.54 | Normalized accuracy (%) | 80.2 |
| Open Korean LLM - Ko-IFEval | 36.24 | Strict accuracy, prompt/instruction mean (%) | 75.3 |
| Open Korean LLM - KorNAT-Helpful | 48.23 | Normalized accuracy (%) | 65.8 |
| Open Korean LLM - KorNAT-Harmless | 63.59 | Normalized accuracy (%) | 64.7 |
| Open Korean LLM - Ko-Winogrande | 59.43 | Accuracy (%) | 46 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=ko-qwen2-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.