Loading data...
AA Omniscience - Science, Engineering & Mathematics: leaderboard
Metric: Accuracy (%). Source: artificialanalysis.ai. 513 models tracked.
Top models
| # | Model | Score |
|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | 62 |
| 2 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | 61.7 |
| 3 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 61.28 |
| 4 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 60 |
| 5 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | 58.2 |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 57.52 |
| 7 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 56.51 |
| 8 | Claude Opus 5 (Adaptive Reasoning, High Effort) | 56.21 |
| 9 | GPT-5.6 Sol (Max) | 55.7 |
| 10 | Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) | 55.2 |
| 11 | GPT-5.6 Sol (Medium) | 54.5 |
| 12 | GPT-5.6 Sol (High) | 54.3 |
| 13 | GPT-6 (xHigh) | 54.3 |
| 14 | Claude Opus 5 (Adaptive Reasoning, Low Effort) | 54.01 |
| 15 | GPT-6 (Max) | 54 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-science-engineering-mathematics · How It Works · Data refreshed daily, snapshot 2026-09-05.