Official repository of the ICML2025 paper “Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination”
-
Updated
Jun 30, 2025 - Python
#
dynamic-benchmark
Here are 2 public repositories matching this topic...
Replication package for PROBE-SWE: a dynamic benchmark to generate, validate, and analyze data-induced cognitive biases in GPAI on typical software-engineering dilemmas.
benchmarking reproducible-research prolog openai software-engineering llama dataset-generation reasoning cognitive-bias replication-package bias-detection ai-evaluation llm-evaluation deepseek llm-as-a-judge gpt-4o dynamic-benchmark general-purpose-ai probe-swe bias-sensitivity
-
Updated
Aug 14, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the dynamic-benchmark topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the dynamic-benchmark topic, visit your repo's landing page and select "manage topics."