KOR-Orca-Platypus-13B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1379 ± 17, rank #2059 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.06 | Accuracy (%) | 87.3 |
| Open Korean LLM - KorNAT-Helpful | 47.27 | Normalized accuracy (%) | 55 |
| Open Korean LLM - KorNAT-CKA | 22.64 | Normalized accuracy (%) | 40.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.14 | Exact match, flexible extract (%) | 35.8 |
| Open Korean LLM - KorNAT-Harmless | 61.56 | Normalized accuracy (%) | 31 |
| Open Korean LLM Leaderboard | 31.95 | Average Score (%) | 30.2 |
| Open Ko-LLM Leaderboard | 31.95 | Average (%) | 29.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - Ko-IFEval | 16.26 | Strict accuracy, prompt/instruction mean (%) | 11.4 |
Interactive version: theaggregate.ai/model?slug=kor-orca-platypus-13b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.