Solar Open 100B (Reasoning) — benchmark results
Solar Open 100B evaluated with reasoning enabled. Provider: Upstage. Released 2025-12-30. Access: Open.
Unified ELO 1583 ± 19, rank #522 of 1776 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - Dart | 28 | Accuracy (%) | 70.8 |
| AA IFBench | 57.69 | Accuracy (%) | 69.2 |
| AA Humanity's Last Exam | 9.18 | Accuracy (%) | 58.8 |
| AA Omniscience - Software Engineering (SWE) - Python | 23.5 | Accuracy (%) | 57.7 |
| AA Omniscience - Software Engineering (SWE) - Swift | 40 | Accuracy (%) | 56 |
| AA-LCR | 36 | Score (self-reported) | 55.6 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 20 | Accuracy (%) | 54.9 |
| AA Omniscience - Software Engineering (SWE) - R | 12 | Accuracy (%) | 52 |
| AA TAU-2 Bench | 48.25 | Accuracy (%) | 51.6 |
| AA Omniscience - Software Engineering (SWE) - Rust | 50 | Accuracy (%) | 50.1 |
| Artificial Analysis Intelligence Index | 15.15 | Intelligence Index | 49.8 |
| AA Global-MMLU-Lite | 81.58 | Accuracy (%) | 49.6 |
Interactive version: theaggregate.ai/model?slug=solar-open-100b-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.