chain-of-thought-hub
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
GraphCanon updated Oct 11, 2026 · GitHub synced Oct 11, 2026
66views this month
Decision brief
Chain-of-Thought Hub measures the performance of large language models (LLMs) on complex tasks by using carefully selected datasets across various domains such as math, science, coding, and knowledge. It evaluates if LLM
Good fit when
- Use Chain-of-Thought Hub when you need to benchmark smaller LLMs against larger ones for complex reasoning abilities.
- Consider using this tool if your project aims to assess the performance of models in detailed tasks that require nuanced understanding and multi-step reasoning.
Avoid when
- Do not use Chain-of-Thought Hub if your focus is on general conversational capabilities rather than specific, challenging problem-solving tasks.
- Avoid this tool if you are primarily interested in simpler language processing tasks that do not involve chain-of-thought prompting or complex datasets.
- Requirements:
- Min 8 GB RAM; Chain-of-Thought Hub is designed to be integrated into environments for evaluating LLMs using Jupyter Notebooks
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (797d since push)
- As of Oct 11, 2026
- Provenance
- Not a fork · Personal account
- As of Oct 11, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/FranxYao/chain-of-thought-hubSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Chain-of-Thought Hub measures the performance of Large Language Models on complex tasks including math, science, symbolic manipulation, coding, and long-context understanding. It aims to assess if smaller models can match or compete with larger ones in these domains.
Capability facts
- Languages
- jupyter notebook
Source: github.language · Oct 11, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Oct 11, 2026)
| Main | HumanEval | Python coding |Source link
Tags
README
Chain of Thought Hub: Measuring LLMs' Reasoning Performance "A fantasy graph illustrating a chain of stars in a dark night with blue sky, digital art, super resolution". Midjourney V5 By Yao Fu, Litu Ou, Mingyu Chen, Yuhao Wan, Hao Peng, Tushar Khot, Wenhu Chen From University of...
For agents
This page has a .md twin and JSON over the API.