# CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

arXiv: https://arxiv.org/abs/2603.02236 · HTML: https://mlsanity.com/paper/2603.02236/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators](https://mlsanity.com/paper/2502.14752/) (2025)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [CUDA-LLM: LLMs Can Write Efficient CUDA Kernels](https://mlsanity.com/paper/2506.09092/) (2025)
- [STARK: Strategic Team of Agents for Refining Kernels](https://mlsanity.com/paper/2510.16996/) (2025)
- [ConCuR: Conciseness Makes State-of-the-Art Kernel Generation](https://mlsanity.com/paper/2510.07356/) (2025)

## Built on by (most cited first, 10 of 10)

- [SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits](https://mlsanity.com/paper/2603.19173/) (2026)
- [StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning](https://mlsanity.com/paper/2603.02637/) (2026)
- [Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization](https://mlsanity.com/paper/2603.28342/) (2026)
- [From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation](https://mlsanity.com/paper/2606.16231/) (2026)
- [Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels](https://mlsanity.com/paper/2607.24762/) (2026)
- [CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging](https://mlsanity.com/paper/2605.08455/) (2026)
- [CodegenBench: Can LLMs Write Efficient Code Across Architectures?](https://mlsanity.com/paper/2606.04023/) (2026)
- [PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX](https://mlsanity.com/paper/2608.17379/) (2026)
- [CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language](https://mlsanity.com/paper/2609.00058/) (2026)
- [GPUPhysBench: Benchmarking Coding Agents for Correct and Efficient GPU Physics Simulation](https://mlsanity.com/paper/2609.35639/) (2026)

## Abstract (arXiv)

Recent studies have demonstrated the potential of Large Language Models (LLMs) in generating GPU Kernels. Current benchmarks focus on the translation of high-level languages into CUDA, overlooking the more general and challenging task of text-to-CUDA generation. Furthermore, given the hardware-specific and performance-critical features of GPU programming, accurately assessing the performance of LLM-generated GPU programs is nontrivial. In this work, we introduce CUDABench, a comprehensive benchmark designed to evaluate the text-to-CUDA capabilities of LLMs. First, we construct CUDABench-Set, which covers Breadth-Depth-Difficulty evaluation space in diverse application domains, including artificial intelligence, scientific computing, and data analytics, etc. Furthermore, we propose CUDABench-Score and Generative Verification Pipeline that assess (1) compilation correctness, (2) functional consistency through execution-based verification, and (3) a novel roofline-based metric, Performance-Score. Benchmarking state-of-the-art LLMs reveals insightful findings and challenges of text-to-CUDA, such as a notable mismatch between high compilation success rates and low functional correctness, a lack of domain-specific algorithmic knowledge, and suboptimal utilization of GPU hardware resources. Our benchmark is available at https://github.com/CUDA-Bench/CUDABench.