G9v3-39A5B: benchmark results
Provider: AI9Stars. Released 2026-08-20. Access: Open.
Aggregate Rating 1629 ± 37, rank #758 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - C | 45 | Accuracy (%) | 74.7 |
| AA GPQA Diamond | 80.51 | Accuracy (%) | 67.6 |
| AA Omniscience - Software Engineering (SWE) - Go | 20 | Accuracy (%) | 62.5 |
| AA Humanity's Last Exam | 17.47 | Accuracy (%) | 62.4 |
| AA Omniscience - Software Engineering (SWE) - Swift | 36 | Accuracy (%) | 60.6 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 22.22 | Accuracy (%) | 60.1 |
| AA Omniscience - Software Engineering (SWE) - Python | 19.5 | Accuracy (%) | 56.1 |
| Tau3 Banking | 22.06 | Success Rate (%) | 55.7 |
| AA Long Context Reasoning | 65.33 | Accuracy (%) | 54.7 |
| AA Omniscience - Software Engineering (SWE) - R | 10 | Accuracy (%) | 53.4 |
| AA GDPval | 1109.37 | ELO | 50.6 |
| AA Omniscience - Software Engineering (SWE) - Rust | 46 | Accuracy (%) | 48.6 |
Interactive version: theaggregate.ai/model?slug=g9v3-39a5b · How It Works · Data refreshed daily, snapshot 2026-11-08.