IndustryCode - MATLAB: leaderboard
Metric: Pass@1 (%) on the MATLAB main problems of the IndustryCode test split (106 main problems decomposed into 499 sub-problems; industrial Python, C++, MATLAB and Stata projects with test cases), each main problem solved by implementing its sub-problems with cumulative context and integrating them; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 37.5 |
| 2 | Gemini 3 Pro | 37.5 |
| 3 | Claude Opus 4.5 | 31.3 |
| 4 | Gemini 2.5 Pro | 25 |
| 5 | Kimi K2 | 25 |
| 6 | Grok 4.1 | 25 |
| 7 | Kimi K2 (Thinking) | 18.8 |
| 8 | Qwen 3 Max (Thinking) | 18.8 |
| 9 | GLM-4.7 (Non-reasoning) | 18.8 |
| 10 | Qwen 3 Coder Plus | 18.8 |
| 11 | GPT-5.2 | 12.5 |
| 12 | Claude Haiku 4.5 | 12.5 |
| 13 | GPT-5.1 | 12.5 |
| 14 | Qwen 3 Max | 12.5 |
| 15 | DeepSeek V3.2 Exp | 6.3 |
Interactive version: theaggregate.ai/benchmark?slug=industrycode-matlab · How It Works · Data refreshed daily, snapshot 2026-10-07.