Merge_test01: benchmark results
Provider: Other. Access: Open.
Unified ELO 1495 ± 17, rank #1142 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 35.47 | EQ-Bench score | 85.6 |
| Open Korean LLM Leaderboard | 41.37 | Average Score (%) | 82.4 |
| Open Ko-LLM Leaderboard | 41.37 | Average (%) | 82.3 |
| Open Korean LLM - KorNAT-Harmless | 65.27 | Normalized accuracy (%) | 79.6 |
| Open Korean LLM - KorNAT-Helpful | 49.4 | Normalized accuracy (%) | 79.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 39.5 | Exact match, flexible extract (%) | 73.9 |
| Open Korean LLM - Ko-Winogrande | 62.04 | Accuracy (%) | 65.8 |
| Open Korean LLM - Ko-IFEval | 31.51 | Strict accuracy, prompt/instruction mean (%) | 60.2 |
| Open Korean LLM - KorNAT-CKA | 24.03 | Normalized accuracy (%) | 49 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
Interactive version: theaggregate.ai/model?slug=merge-test01 · How It Works · Data refreshed daily, snapshot 2026-09-19.