DataVortexS-10.7B-dpo-v1.6: benchmark results
Provider: Other. Access: Open.
Unified ELO 1467 ± 17, rank #1399 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 80.09 | Normalized accuracy (%) | 99 |
| Open Korean LLM - KorNAT-CKA | 35.25 | Normalized accuracy (%) | 95.4 |
| Open Korean LLM - Ko-Winogrande | 69.46 | Accuracy (%) | 94.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM Leaderboard | 38.76 | Average Score (%) | 68.5 |
| Open Ko-LLM Leaderboard | 38.76 | Average (%) | 68.4 |
| Open Korean LLM - KorNAT-Helpful | 48.3 | Normalized accuracy (%) | 67.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 30.71 | Exact match, flexible extract (%) | 65.1 |
| Open Korean LLM - Ko-EQ-Bench | 6.47 | EQ-Bench score | 52.4 |
| Open Korean LLM - Ko-IFEval | 25.94 | Strict accuracy, prompt/instruction mean (%) | 37.5 |
Interactive version: theaggregate.ai/model?slug=datavortexs-10-7b-dpo-v1-6 · How It Works · Data refreshed daily, snapshot 2026-09-19.