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

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

Top models

#ModelScore
1GPT-5.5 (xHigh)92
2GPT-5.6 Sol (xHigh)86
3GPT-5.5 (Medium)86
4GPT-5.6 Sol (High)86
5GPT-5.3 Codex (xHigh)86
6GPT-5.6 Sol (Medium)86
7GPT-5.6 Sol (Low)86
8GPT-5.6 Sol (Max)84
9Qwen 3.6 Max Preview82
10GPT-5.5 (High)82
11GPT-5.5 (Low)82
12Claude Opus 4.8 (Adaptive Reasoning, Max Effort)82
13GPT-5.4 Mini (Medium)80
14Gemini 3.5 Flash (High)80
15Gemini 3 Pro (Preview) (High)80

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