SOLAR-10.7B-merge-dpo_v1: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1484 ± 18, rank #1241 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 34.02 | Normalized accuracy (%) | 93.3 |
| Open Korean LLM - KorNAT-Harmless | 70.06 | Normalized accuracy (%) | 93.3 |
| Open Korean LLM - Ko-IFEval | 42.43 | Strict accuracy, prompt/instruction mean (%) | 86.3 |
| Open Korean LLM - Ko-Winogrande | 64.64 | Accuracy (%) | 79.8 |
| Open Korean LLM - Ko-EQ-Bench | 28.81 | EQ-Bench score | 76.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 39.12 | Exact match, flexible extract (%) | 73.5 |
| Open Korean LLM Leaderboard | 39.67 | Average Score (%) | 73.3 |
| Open Ko-LLM Leaderboard | 39.67 | Average (%) | 73 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Helpful | 47.25 | Normalized accuracy (%) | 54.7 |
Interactive version: theaggregate.ai/model?slug=solar-10-7b-merge-dpo-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.