Solar Open2 250B: benchmark results
Provider: Upstage. Released 2026-07-22. Access: Open.
Unified ELO 1622 ± 1, rank #346 of 1761 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - HTML | 54 | Accuracy (%) | 91.1 |
| AA Omniscience - Software Engineering (SWE) - C | 58 | Accuracy (%) | 88.7 |
| AA Omniscience - Software Engineering (SWE) - Swift | 52 | Accuracy (%) | 86.7 |
| AA Humanity's Last Exam | 28.54 | Accuracy (%) | 80.7 |
| AA CritPt | 5.71 | Accuracy (%) | 80.3 |
| AA Omniscience | -1.77 | Score | 79.5 |
| Artificial Analysis Intelligence Index | 29.05 | Intelligence Index | 79.5 |
| AA GPQA Diamond | 85.66 | Accuracy (%) | 79.4 |
| BenchmarkList ECI | 132.43 | Capability Index (ECI) | 78.5 |
| AA Omniscience - Software Engineering (SWE) - R | 16 | Accuracy (%) | 72.5 |
| AA Long Context Reasoning | 71.67 | Accuracy (%) | 70.7 |
| AA Omniscience - Software Engineering (SWE) - Python | 24 | Accuracy (%) | 70.3 |
Interactive version: theaggregate.ai/model?slug=solar-open2-250b · How It Works · Data refreshed daily, snapshot 2026-09-05.