Omni-MATH Benchmark

What is Omni-MATH?

Omni-MATH focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems…

Released

2024-10-10

Evaluates

强推理, Strong Reasoning, 数学, Math, 大语言模型, LLM, 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/Omni-MATH

Omni-MATH paper, code and dataset

• Paper https://arxiv.org/abs/2410.07985
• Code https://github.com/KbsdJames/Omni-MATH
• Dataset https://huggingface.co/datasets/KbsdJames/Omni-MATH

Which sources cite Omni-MATH?

• Omni-MATH

Related 强推理, Strong Reasoning, 数学, Math, 大语言模型, LLM, 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