mergecat-v0.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1460 ± 17, rank #1445 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 74.19 | Accuracy (%) | 99.3 |
| Open Korean LLM - KorNAT-Helpful | 69.6 | Normalized accuracy (%) | 99 |
| Open Korean LLM - KorNAT-Harmless | 79.44 | Normalized accuracy (%) | 98.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 28.28 | Normalized accuracy (%) | 96.6 |
| Open Korean LLM - KorNAT-CKA | 27.33 | Normalized accuracy (%) | 69.3 |
| Open Korean LLM Leaderboard | 38.33 | Average Score (%) | 66.3 |
| Open Ko-LLM Leaderboard | 38.33 | Average (%) | 66.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 19.94 | Exact match, flexible extract (%) | 51.7 |
| Open Korean LLM - Ko-EQ-Bench | 3.14 | EQ-Bench score | 49.1 |
| Open Korean LLM - Ko-IFEval | 26.94 | Strict accuracy, prompt/instruction mean (%) | 41.1 |
Interactive version: theaggregate.ai/model?slug=mergecat-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.