KoSOLAR-10.7B-DPO-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1359 ± 18, rank #2179 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 68.08 | Normalized accuracy (%) | 91.5 |
| Open Korean LLM - KorNAT-CKA | 30.64 | Normalized accuracy (%) | 84.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 26.76 | Exact match, flexible extract (%) | 60.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-Winogrande | 59.59 | Accuracy (%) | 47.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 21.89 | Strict accuracy, prompt/instruction mean (%) | 22.1 |
| Open Korean LLM Leaderboard | 30.29 | Average Score (%) | 18.1 |
| Open Ko-LLM Leaderboard | 30.29 | Average (%) | 18 |
| Open Korean LLM - KorNAT-Helpful | 37.67 | Normalized accuracy (%) | 2.7 |
Interactive version: theaggregate.ai/model?slug=kosolar-10-7b-dpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.