mergekit_v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1338 ± 20, rank #2300 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.17 | Accuracy (%) | 77.4 |
| Open Korean LLM - KorNAT-Helpful | 48.6 | Normalized accuracy (%) | 70.2 |
| Open Korean LLM - KorNAT-CKA | 26.2 | Normalized accuracy (%) | 62.8 |
| Open Korean LLM - Ko-IFEval | 31.37 | Strict accuracy, prompt/instruction mean (%) | 59.4 |
| Open Korean LLM - KorNAT-Harmless | 63.13 | Normalized accuracy (%) | 56.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 16.45 | Exact match, flexible extract (%) | 46.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM Leaderboard | 29 | Average Score (%) | 9.1 |
| Open Ko-LLM Leaderboard | 29 | Average (%) | 9 |
| Open Korean LLM - Ko-EQ-Bench | -28.06 | EQ-Bench score | 0.4 |
Interactive version: theaggregate.ai/model?slug=mergekit-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.