SOLAR_merge_DPOv3: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1495 ± 17, rank #1141 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 70.44 | Normalized accuracy (%) | 93.6 |
| Open Korean LLM - Ko-EQ-Bench | 43.63 | EQ-Bench score | 93.2 |
| Open Korean LLM - KorNAT-CKA | 33.59 | Normalized accuracy (%) | 92.5 |
| Open Korean LLM - Ko-Winogrande | 66.3 | Accuracy (%) | 88.1 |
| Open Korean LLM Leaderboard | 40.88 | Average Score (%) | 79.2 |
| Open Ko-LLM Leaderboard | 40.88 | Average (%) | 79.1 |
| Open Korean LLM - KorNAT-Helpful | 48.58 | Normalized accuracy (%) | 69.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 26.46 | Exact match, flexible extract (%) | 60.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-IFEval | 29.42 | Strict accuracy, prompt/instruction mean (%) | 51.8 |
Interactive version: theaggregate.ai/model?slug=solar-merge-dpov3 · How It Works · Data refreshed daily, snapshot 2026-09-19.