IndustryCode - Sub-Problems: leaderboard
IndustryCode (2026) is a code-generation benchmark of hierarchical industrial programming problems in Python, C++, MATLAB and Stata, each main problem decomposed into sub-problems checked by test cases. This board is Pass@1 in percent on the sub-problems, the unweighted mean over the four languages; higher is better.
Metric: Pass@1 (%) on the sub-problems of the IndustryCode test split (106 main problems decomposed into 499 sub-problems; industrial Python, C++, MATLAB and Stata projects with test cases), unweighted mean of the Python, C++, MATLAB and Stata sub-problem pass rates; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 68.1 | #160 | |
| 2 | Claude Sonnet 4.5 | 64.4 | #261 | |
| 3 | Gemini 3 Pro | 63.4 | #145 | |
| 4 | Claude Haiku 4.5 | 57.4 | #583 | |
| 5 | Qwen 3 Max | 55.9 | #415 | |
| 6 | Grok 4.1 | 53.6 | #462 | |
| 7 | GPT-5.2 | 53.4 | #185 | |
| 8 | Gemini 2.5 Pro | 51.6 | #276 | |
| 9 | Seed 1.8 | Thinking | 50.1 | #252 |
| 10 | GPT-5.1 | 48.1 | #240 | |
| 11 | GLM-4.7 | Thinking | 47 | #380 |
| 12 | Kimi K2 | 46.8 | #443 | |
| 13 | Kimi K2 (Thinking) | 37.6 | ||
| 14 | Qwen 3 Coder Plus | 36.1 | #720 | |
| 15 | DeepSeek V3.2 Exp | 35.3 | #439 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=industrycode-sub-problems · How It Works · Data refreshed daily, snapshot 2026-11-21.