AA-Omniscience Index - Software Engineering (SWE) - Swift: leaderboard

Metric: Omniscience Index. Source: artificialanalysis.ai. 527 models tracked.

Top models

#ModelScore
1Claude Opus 5 (Adaptive Reasoning, Max Effort)92
2Claude Opus 4.8 (Adaptive Reasoning, Max Effort)88
3GPT-6 (xHigh)88
4Claude Opus 4.7 (Adaptive Reasoning, Max Effort)84
5GPT-5.5 (xHigh)76
6GPT-6 (Max)76
7GPT-6 (Low)72
8GPT-5.5 (High)68
9GPT-5.6 Sol (Medium)68
10GPT-6 (High)68
11GPT-5.6 Sol (Low)68
12GPT-6 (Medium)68
13GPT-5.5 (Low)68
14Gemini 3.7 Flash (Low)68
15Gemini 3 Pro (Preview) (Low)68

Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-index-software-engineering-swe-swift · How It Works · Data refreshed daily, snapshot 2026-09-19.