AA-Omniscience Index - Software Engineering (SWE) - HTML: leaderboard
Metric: Omniscience Index. Source: artificialanalysis.ai. 527 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 92 |
| 2 | GPT-6 (Max) | 92 |
| 3 | GPT-6 (xHigh) | 92 |
| 4 | GPT-5.5 (xHigh) | 88 |
| 5 | GPT-6 (High) | 88 |
| 6 | GPT-6 (Medium) | 88 |
| 7 | GPT-5.5 (High) | 84 |
| 8 | GPT-5.5 (Medium) | 84 |
| 9 | GPT-6 (Low) | 84 |
| 10 | GPT-5.6 Sol (High) | 80 |
| 11 | GPT-5.6 Sol (xHigh) | 78 |
| 12 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 78 |
| 13 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 76 |
| 14 | GPT-5.4 (xHigh) | 72 |
| 15 | GPT-5.6 Sol (Low) | 72 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-index-software-engineering-swe-html · How It Works · Data refreshed daily, snapshot 2026-09-19.