Loading data...
AA Omniscience - Software Engineering (SWE): leaderboard
Metric: Accuracy (%). Source: artificialanalysis.ai. 514 models tracked.
Top models
| # | Model | Score |
|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | 92.4 |
| 2 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 91.1 |
| 3 | GPT-6 (xHigh) | 91 |
| 4 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | 90.7 |
| 5 | GPT-6 (Max) | 90.5 |
| 6 | GPT-6 (Medium) | 90.2 |
| 7 | GPT-6 (High) | 89.9 |
| 8 | GPT-6 (Low) | 89.1 |
| 9 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 89.1 |
| 10 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | 87.5 |
| 11 | GPT-5.5 (xHigh) | 86.2 |
| 12 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 86 |
| 13 | GPT-5.5 (High) | 85.7 |
| 14 | GPT-5.6 Sol (Max) | 85.5 |
| 15 | GPT-5.5 (Medium) | 85.5 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-software-engineering-swe · How It Works · Data refreshed daily, snapshot 2026-09-05.