Ko-PlatYi-6B-kiwi: benchmark results
Provider: Other. Access: Open.
Unified ELO 1333 ± 17, rank #2332 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 61.17 | Accuracy (%) | 60.3 |
| Open Korean LLM - KorNAT-CKA | 21.67 | Normalized accuracy (%) | 36 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Helpful | 44.75 | Normalized accuracy (%) | 32.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.16 | Exact match, flexible extract (%) | 24.3 |
| Open Korean LLM - KorNAT-Harmless | 60.99 | Normalized accuracy (%) | 21.8 |
| Open Korean LLM Leaderboard | 29.43 | Average Score (%) | 12 |
| Open Ko-LLM Leaderboard | 29.43 | Average (%) | 11.9 |
| Open Korean LLM - Ko-IFEval | 0.5 | Strict accuracy, prompt/instruction mean (%) | 2.6 |
Interactive version: theaggregate.ai/model?slug=ko-platyi-6b-kiwi · How It Works · Data refreshed daily, snapshot 2026-09-19.