AA Omniscience - Software Engineering (SWE) - Go: leaderboard
Go-language slice of AA Omniscience SWE, testing factual knowledge of Go syntax, standard libraries, tooling, and engineering practice.
Metric: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around April 2027. 294 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 (Thinking) | 70 | #83 (Claude Opus 4.5) |
| 2 | Claude Opus 4.5 (Non-reasoning) | 66 | #83 (Claude Opus 4.5) |
| 3 | Kimi K3 (Max) | 60 | #30 (Kimi K3) |
| 4 | Gemini 3 Pro (Preview) (High) | 60 | #66 (Gemini 3 Pro (Preview)) |
| 5 | Claude Sonnet 4.5 (Non-reasoning) | 58 | #142 (Claude Sonnet 4.5) |
| 6 | Kimi K3 (Low) | 56 | #30 (Kimi K3) |
| 7 | Claude Sonnet 4.5 (Thinking) | 52 | #142 (Claude Sonnet 4.5) |
| 8 | Kimi K2.7 Code | 52 | #89 |
| 9 | Kimi K2.5 (Thinking) | 50 | #144 (Kimi K2.5) |
| 10 | DeepSeek V4 Flash (Reasoning, Max Effort) | 50 | #137 (DeepSeek V4 Flash) |
| 11 | GPT-5 (Medium) | 46 | #98 (GPT-5) |
| 12 | Hy3-preview (Non-reasoning) | 46 | #157 (Hy3-preview) |
| 13 | DeepSeek V4 Pro (Reasoning, Max Effort) | 46 | #102 (DeepSeek V4 Pro) |
| 14 | Nex N2 Pro | 42.86 | #107 |
| 15 | Hy3 | 42 | #93 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-software-engineering-swe-go · How It Works · Data refreshed daily, snapshot 2026-10-20.