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

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

Top models

#ModelScore
1GPT-5.6 Sol (Max)92.22
2GPT-5.5 (xHigh)91.11
3GPT-5.4 (xHigh)91.11
4GPT-5.6 Sol (xHigh)91.11
5GPT-5.6 Sol (High)91.11
6GPT-5.3 Codex (xHigh)90
7GPT-5.6 Sol (Medium)90
8GPT-5.5 (High)88.89
9GPT-5.5 (Low)88.89
10GPT-5.6 Sol (Low)87.78
11GPT-5.5 (Medium)86.67
12GPT-5.4 (Low)86.67
13GPT-5.5 Instant80
14GPT-5.6 Terra (High)78.89
15GPT-5.6 Sol (Non-reasoning)78.89

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