Kosy-platypus2-13B-v5: benchmark results
Provider: Other. Access: Open.
Unified ELO 1337 ± 18, rank #2305 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 62.75 | Accuracy (%) | 70.4 |
| Open Korean LLM - KorNAT-Helpful | 47.38 | Normalized accuracy (%) | 56 |
| Open Korean LLM - KorNAT-Harmless | 62.48 | Normalized accuracy (%) | 44.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.75 | Exact match, flexible extract (%) | 37.2 |
| Open Korean LLM - KorNAT-CKA | 20.44 | Normalized accuracy (%) | 29.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 29.61 | Average Score (%) | 12.5 |
| Open Ko-LLM Leaderboard | 29.61 | Average (%) | 12.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - Ko-IFEval | 2.77 | Strict accuracy, prompt/instruction mean (%) | 4.7 |
Interactive version: theaggregate.ai/model?slug=kosy-platypus2-13b-v5 · How It Works · Data refreshed daily, snapshot 2026-09-19.