miniCTX Benchmark

What is miniCTX?

A context-rich benchmark for evaluating neural theorem proving in realistic scenarios, providing premises, full context, multi-source benchmark, and temporal…

Released

2024-08-03

Evaluates

强推理, Strong Reasoning, 数学, Math, 科学智能, AI for Science, 逻辑推理, Reasoning, 数理能力, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/miniCTX

miniCTX code and dataset

• Code https://github.com/cmu-l3/minictx-eval
• Dataset https://huggingface.co/datasets/l3lab/miniCTX

Which sources cite miniCTX?

• miniCTX

Related 强推理, Strong Reasoning, 数学, Math, 科学智能, AI for Science, 逻辑推理, Reasoning, 数理能力, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench