AA Omniscience - Software Engineering (SWE) - Go Leaderboard

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

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

#	Model	Score
1	GPT-5.6 Sol (xHigh)	86
2	GPT-5.5 (High)	84
3	GPT-5.6 Sol (High)	84
4	GPT-5.6 Sol (Medium)	84
5	GPT-5.6 Sol (Low)	84
6	GPT-5.5 (Medium)	82
7	GPT-5.6 Sol (Max)	82
8	GPT-5.5 (xHigh)	80
9	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)	80
10	GPT-5.6 Sol (Non-reasoning)	80
11	GPT-5.4 (xHigh)	78
12	GPT-5.5 (Low)	78
13	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	78
14	GPT-5.6 Terra (Max)	74
15	GPT-5.4 (Low)	74