nox_DPOv3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1461 ± 18, rank #1439 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 75.14 | Accuracy (%) | 99.6 |
| Open Korean LLM - KorNAT-Helpful | 72.35 | Normalized accuracy (%) | 99.3 |
| Open Korean LLM - KorNAT-Harmless | 80.13 | Normalized accuracy (%) | 99.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - KorNAT-CKA | 30.66 | Normalized accuracy (%) | 84.4 |
| Open Korean LLM Leaderboard | 38.35 | Average Score (%) | 66.6 |
| Open Ko-LLM Leaderboard | 38.35 | Average (%) | 66.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.06 | Exact match, flexible extract (%) | 54.3 |
| Open Korean LLM - Ko-IFEval | 25.96 | Strict accuracy, prompt/instruction mean (%) | 37.6 |
| Open Korean LLM - Ko-EQ-Bench | -0.05 | EQ-Bench score | 5.9 |
Interactive version: theaggregate.ai/model?slug=nox-dpov3 · How It Works · Data refreshed daily, snapshot 2026-09-19.