GPT-6 Sol (Max): benchmark results
Provider: OpenAI. Released 2026-09-22. Access: API.
Aggregate Rating 1915 ± 8, rank #34 of 2178 rated models, from 270 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Agent Arena - Steerability | 11.92 | Steerability (%) | 100 |
| DeepsecBench-AA | 46.32 | Median F2 (%) | 100 |
| AA CritPt | 30.86 | Accuracy (%) | 98 |
| OTIS Mock AIME 2024-25 | 100 | Accuracy (%) | 97.9 |
| Vals AI CyberBench | 77.98 | Accuracy (%) | 97.8 |
| Epoch AI - GPQA Diamond | 94.32 | Accuracy (%) | 97.4 |
| WebDev Arena (Fullstack) | 1705 | Arena Score | 97.4 |
| ZeroBench | 41 | Score (%) | 97.3 |
| AA Long Context Reasoning | 83.67 | Accuracy (%) | 97.1 |
| WebDev Arena (Consumer Product) | 1644 | Arena Score | 97.1 |
| WebDev Arena (Data & Analytics) | 1623 | Arena Score | 97.1 |
| AutomationBench-AA - Sales - Raw Objective Completion | 88.68 | Raw Objective Completion (%) | 96.8 |
Interactive version: theaggregate.ai/model?slug=gpt-6-sol-max · How It Works · Data refreshed daily, snapshot 2026-11-07.