KOR-Orca-Platypus-13B-v3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1350 ± 17, rank #2238 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.14 | Accuracy (%) | 87.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.9 | Exact match, flexible extract (%) | 38 |
| Open Korean LLM - KorNAT-CKA | 21.11 | Normalized accuracy (%) | 32.8 |
| Open Korean LLM - KorNAT-Helpful | 44.77 | Normalized accuracy (%) | 32.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - KorNAT-Harmless | 61.2 | Normalized accuracy (%) | 24.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 30.15 | Average Score (%) | 17.3 |
| Open Ko-LLM Leaderboard | 30.15 | Average (%) | 17.2 |
| Open Korean LLM - Ko-IFEval | 3.74 | Strict accuracy, prompt/instruction mean (%) | 5.3 |
Interactive version: theaggregate.ai/model?slug=kor-orca-platypus-13b-v3 · How It Works · Data refreshed daily, snapshot 2026-09-19.