ko-platypus-kiwi-13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1380 ± 17, rank #2050 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.8 | Accuracy (%) | 80.8 |
| Open Korean LLM - KorNAT-Helpful | 46.25 | Normalized accuracy (%) | 43.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.52 | Exact match, flexible extract (%) | 36.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Harmless | 61.55 | Normalized accuracy (%) | 30.8 |
| Open Korean LLM Leaderboard | 32.06 | Average Score (%) | 30.8 |
| Open Ko-LLM Leaderboard | 32.06 | Average (%) | 30.5 |
| Open Korean LLM - KorNAT-CKA | 19.97 | Normalized accuracy (%) | 27.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 18.67 | Strict accuracy, prompt/instruction mean (%) | 14.3 |
Interactive version: theaggregate.ai/model?slug=ko-platypus-kiwi-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.