AA-Omniscience Index - Software Engineering (SWE): leaderboard
Metric: Omniscience Index. Source: artificialanalysis.ai. 527 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (xHigh) | 84.2 |
| 2 | GPT-6 (Medium) | 83 |
| 3 | GPT-6 (Max) | 82.8 |
| 4 | GPT-6 (High) | 82.6 |
| 5 | GPT-6 (Low) | 80.9 |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 74.3 |
| 7 | GPT-5.5 (xHigh) | 72.6 |
| 8 | GPT-5.5 (High) | 71.9 |
| 9 | GPT-5.6 Sol (Max) | 71.4 |
| 10 | GPT-5.5 (Medium) | 71.3 |
| 11 | GPT-5.6 Sol (xHigh) | 71 |
| 12 | GPT-5.3 Codex (xHigh) | 70.7 |
| 13 | GPT-5.6 Sol (High) | 68.1 |
| 14 | GPT-5.4 (xHigh) | 67.9 |
| 15 | GPT-5.6 Sol (Medium) | 66.6 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-index-software-engineering-swe · How It Works · Data refreshed daily, snapshot 2026-09-19.