IndustryCode - C++ 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 C++ sub-problems, each generated with the earlier steps as context; higher is better.
Metric: Pass@1 (%) on the C++ 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), each sub-problem generated with the main-problem description and the code of earlier steps as context; 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 | 70.9 | #160 | |
| 2 | Qwen 3 Max | 70.4 | #415 | |
| 3 | GPT-5.2 | 67.9 | #185 | |
| 4 | Gemini 3 Pro | 66 | #145 | |
| 5 | GPT-5.1 | 63.5 | #240 | |
| 6 | Claude Haiku 4.5 | 61.7 | #583 | |
| 7 | Gemini 2.5 Pro | 58.6 | #276 | |
| 8 | Claude Sonnet 4.5 | 58 | #261 | |
| 9 | Kimi K2 | 54.3 | #443 | |
| 10 | Qwen 3 Coder Plus | 54.3 | #720 | |
| 11 | Seed 1.8 | Thinking | 54.3 | #252 |
| 12 | Grok 4.1 | 51.2 | #462 | |
| 13 | GLM-4.7 | Thinking | 46.3 | #380 |
| 14 | Kimi K2 (Thinking) | 25.3 | ||
| 15 | Doubao-Seed-1.6 | Thinking | 17.3 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=industrycode-c-plus-plus-sub-problems · How It Works · Data refreshed daily, snapshot 2026-11-21.