solar-pro2-251215: benchmark results
Provider: Upstage.
Aggregate Rating 1634 ± 31, rank #729 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - Ko-Moral | 82 | Accuracy (%) | 85.6 |
| Horangi 4 - Korean Hate Speech | 66 | Accuracy (%) | 82.2 |
| Horangi 4 - BFCL | 68.22 | Accuracy (%) | 74.4 |
| Horangi 4 - ALT Average | 76.13 | Score (%) | 70.2 |
| Horangi 4 - Ko-MT-Bench | 87.38 | Judge rating (1-10, x10) | 70.2 |
| Horangi 4 - KoBBQ | 91 | Accuracy (%) | 69.2 |
| Horangi 4 - HAE-RAE Bench (Reading Comprehension) | 89 | Accuracy (%) | 64.9 |
| Horangi 4 - Ko-HellaSwag | 81 | Accuracy (%) | 62 |
| Horangi 4 - KMMLU-Pro | 74 | Accuracy (%) | 60.1 |
| Horangi 4 - GLP - Logical Reasoning | 83 | Score (%) | 59.6 |
| Horangi 4 - GLP - General Knowledge | 85.44 | Score (%) | 58.7 |
| Horangi 4 - HAE-RAE Bench (without Reading Comprehension) | 88.89 | Accuracy (%) | 58.2 |
Interactive version: theaggregate.ai/model?slug=solar-pro2-251215 · How It Works · Data refreshed daily, snapshot 2026-11-08.