AA Omniscience - Software Engineering (SWE) - Julia: leaderboard
Julia-language slice of AA Omniscience SWE, testing factual knowledge of Julia syntax, libraries, tooling, and technical-computing practice.
Metric: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around January 2027. 294 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 (Thinking) | 68 | #83 (Claude Opus 4.5) |
| 2 | Claude Opus 4.5 (Non-reasoning) | 56 | #83 (Claude Opus 4.5) |
| 3 | Gemini 3 Pro (Preview) (High) | 56 | #66 (Gemini 3 Pro (Preview)) |
| 4 | Claude Sonnet 4.5 (Non-reasoning) | 52 | #142 (Claude Sonnet 4.5) |
| 5 | Kimi K3 (Max) | 48 | #30 (Kimi K3) |
| 6 | Kimi K2.7 Code | 48 | #89 |
| 7 | Motif 3 | 48 | #190 |
| 8 | Kimi K3 (Low) | 48 | #30 (Kimi K3) |
| 9 | GPT-5 (High) | 44 | #98 (GPT-5) |
| 10 | GPT-5 (Medium) | 40 | #98 (GPT-5) |
| 11 | Gemini 2.5 Pro | 36 | #152 |
| 12 | Kimi K2.6 | 36 | #104 |
| 13 | Claude Sonnet 4.5 (Thinking) | 36 | #142 (Claude Sonnet 4.5) |
| 14 | O3 | 36 | #124 |
| 15 | Qwen 3 235B A22B 2507 (Thinking) | 36 | #260 (Qwen 3 235B A22B 2507) |
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-julia · How It Works · Data refreshed daily, snapshot 2026-10-20.