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

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

Top models

#ModelScore
1GPT-5.5 (High)74
2Claude Opus 4.6 (Adaptive Reasoning, Max Effort)74
3GPT-5.5 (Medium)74
4GPT-5.4 (Low)72
5GPT-5.6 Sol (Medium)72
6Grok 4.5 (High)70
7GPT-5.5 (xHigh)68
8GPT-5.6 Sol (xHigh)68
9GPT-5.6 Sol (High)68
10GPT-5.4 (xHigh)66
11GPT-5.6 Sol (Max)66
12GPT-5.3 Codex (xHigh)66
13GPT-5.5 (Low)64
14GPT-5.6 Sol (Low)64
15Claude Opus 4.8 (Adaptive Reasoning, Max Effort)64

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