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

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

Top models

#ModelScore
1GPT-5.4 (Low)88
2GPT-5.4 (xHigh)84
3GPT-5.3 Codex (xHigh)84
4GPT-5.5 (xHigh)76
5GPT-5.5 (High)76
6GPT-5.5 (Low)76
7Claude Opus 4.7 (Adaptive Reasoning, Max Effort)76
8Claude Opus 4.5 (Thinking)72
9GPT-5.6 Sol (xHigh)72
10GPT-5.4 (Non-reasoning)72
11GPT-5.6 Sol (Medium)72
12GPT-5.6 Sol (Low)72
13GPT-5.6 Terra (Low)72
14Claude Sonnet 5 (Adaptive Reasoning, Max Effort)72
15GPT-5.5 Instant68

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