AA Omniscience - Software Engineering (SWE) - HTML — leaderboard

Metric: Accuracy (%). Source: artificialanalysis.ai. 449 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol (Max)92
2GPT-5.5 (High)90
3GPT-5.5 (Medium)90
4GPT-5.5 (xHigh)88
5GPT-5.6 Sol (xHigh)88
6GPT-5.5 (Low)86
7GPT-5.3 Codex (xHigh)86
8GPT-5.6 Sol (High)84
9GPT-5.6 Sol (Low)84
10GPT-5.4 (xHigh)82
11Claude Opus 4.8 (Adaptive Reasoning, Max Effort)82
12GPT-5.6 Sol (Medium)80
13Gemini 3.1 Pro (Preview)78
14Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)78
15GPT-5.6 Terra (Max)78

Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-software-engineering-swe-html · How the rankings work · Data refreshed daily, snapshot 2026-07-22.