FranxYao/chain-of-thought-hub
Academic benchmark suite evaluating LLMs on complex reasoning tasks using chain-of-thought prompting across math, science, coding, and knowledge domains.
Not currently ranked — collecting fresh signals.
star history
A research framework that systematically benchmarks large language models across diverse reasoning domains including mathematics, science, symbolic manipulation, coding, and factual accuracy. It provides standardized evaluation datasets and metrics to measure model performance on challenging tasks, with a focus on assessing chain-of-thought reasoning capabilities. The work includes implementations for multiple benchmarks like GSM8K, MATH, TheoremQA, BBH, MMLU, and HumanEval.
Frequently asked
- What is FranxYao/chain-of-thought-hub?
- Academic benchmark suite evaluating LLMs on complex reasoning tasks using chain-of-thought prompting across math, science, coding, and knowledge domains.
- Is chain-of-thought-hub open source?
- Yes — FranxYao/chain-of-thought-hub is open source, released under the MIT license.
- What language is chain-of-thought-hub written in?
- FranxYao/chain-of-thought-hub is primarily written in Jupyter Notebook.
- How popular is chain-of-thought-hub?
- FranxYao/chain-of-thought-hub has 2.8k stars on GitHub.
- Where can I find chain-of-thought-hub?
- FranxYao/chain-of-thought-hub is on GitHub at https://github.com/FranxYao/chain-of-thought-hub.