AA Omniscience - Science, Engineering & Mathematics — leaderboard
Metric: Accuracy (%). Source: artificialanalysis.ai. 449 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 54.1 |
| 2 | GPT-5.5 (High) | 52.3 |
| 3 | GPT-5.6 Sol (High) | 52.2 |
| 4 | GPT-5.6 Sol (xHigh) | 52.1 |
| 5 | Grok Build 0.1 | 52.1 |
| 6 | Gemini 3.1 Pro (Preview) | 51.9 |
| 7 | GPT-5.6 Sol (Medium) | 51.9 |
| 8 | Grok 4.5 (High) | 51.8 |
| 9 | Gemini 3 Pro (Preview) (High) | 51.7 |
| 10 | GPT-5.5 (xHigh) | 51.3 |
| 11 | GPT-5.6 Sol (Low) | 51.3 |
| 12 | Gemini 3.5 Flash (High) | 50.1 |
| 13 | GPT-5.5 (Medium) | 49.6 |
| 14 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | 49.4 |
| 15 | Claude Opus 4.5 (Thinking) | 48.5 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-science-engineering-mathematics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.