ko-llama7B-merged: benchmark results
Provider: Other. Access: Open.
Unified ELO 1350 ± 17, rank #2236 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 31.04 | Strict accuracy, prompt/instruction mean (%) | 58.9 |
| Open Korean LLM - KorNAT-Harmless | 62.51 | Normalized accuracy (%) | 45.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.72 | Accuracy (%) | 22 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 3.79 | Exact match, flexible extract (%) | 21.9 |
| Open Ko-LLM Leaderboard | 30.77 | Average (%) | 21.3 |
| Open Korean LLM Leaderboard | 30.77 | Average Score (%) | 21.3 |
| Open Korean LLM - KorNAT-CKA | 13.15 | Normalized accuracy (%) | 4.4 |
| Open Korean LLM - KorNAT-Helpful | 38.38 | Normalized accuracy (%) | 3.5 |
Interactive version: theaggregate.ai/model?slug=ko-llama7b-merged · How It Works · Data refreshed daily, snapshot 2026-09-19.