Korean-OpenOrca-v3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1386 ± 17, rank #2011 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.75 | Accuracy (%) | 86 |
| Open Korean LLM - KorNAT-Harmless | 63.55 | Normalized accuracy (%) | 64.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 12.36 | Exact match, flexible extract (%) | 38.9 |
| Open Korean LLM - KorNAT-Helpful | 45.73 | Normalized accuracy (%) | 38.8 |
| Open Korean LLM Leaderboard | 32.52 | Average Score (%) | 34.5 |
| Open Ko-LLM Leaderboard | 32.52 | Average (%) | 34.2 |
| Open Korean LLM - KorNAT-CKA | 20.82 | Normalized accuracy (%) | 31.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 21.73 | Strict accuracy, prompt/instruction mean (%) | 22 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.18 | Normalized accuracy (%) | 2.3 |
Interactive version: theaggregate.ai/model?slug=korean-openorca-v3 · How It Works · Data refreshed daily, snapshot 2026-09-19.