SOLAR-10.7B-merge-dpo: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1365 ± 17, rank #2139 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 63.9 | Normalized accuracy (%) | 68.1 |
| Open Korean LLM - KorNAT-CKA | 26.81 | Normalized accuracy (%) | 66.8 |
| Open Korean LLM - Ko-IFEval | 32.92 | Strict accuracy, prompt/instruction mean (%) | 64.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-Winogrande | 59.43 | Accuracy (%) | 46 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 8.04 | Exact match, flexible extract (%) | 30.9 |
| Open Korean LLM Leaderboard | 30.88 | Average Score (%) | 22.4 |
| Open Ko-LLM Leaderboard | 30.88 | Average (%) | 22.3 |
| Open Korean LLM - KorNAT-Helpful | 43.15 | Normalized accuracy (%) | 21.6 |
| Open Korean LLM - Ko-EQ-Bench | -1.24 | EQ-Bench score | 3.8 |
Interactive version: theaggregate.ai/model?slug=solar-10-7b-merge-dpo · How It Works · Data refreshed daily, snapshot 2026-09-19.