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

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

Top models

#ModelScore
1GPT-5.3 Codex (xHigh)80
2GPT-5.5 (Low)78
3GPT-5.5 (xHigh)76
4GPT-5.5 (High)76
5GPT-5.5 (Medium)76
6GPT-5.6 Sol (Max)76
7GPT-5.6 Sol (High)76
8GPT-5.6 Sol (xHigh)74
9GPT-5.4 (xHigh)70
10GPT-5.6 Sol (Medium)70
11GPT-5.6 Sol (Low)70
12GPT-5.4 (Low)68
13Claude Opus 4.8 (Adaptive Reasoning, Max Effort)68
14Claude Opus 4.6 (Adaptive Reasoning, Max Effort)66
15Claude Opus 4.7 (Adaptive Reasoning, Max Effort)66

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