Benchmark

S1-Bench

What is S1-Bench?

S1-Bench is a novel benchmark designed to evaluate the performance of LRMs on simple tasks that are more aligned with intuitive System 1 thinking, rather than…

Released: 2025-04-15
Evaluates: 强推理, Strong Reasoning, 理解, Understanding, 指令跟随, Instruct, 系统1, 快思考, LRM, 大语言模型, LLM, 逻辑推理, Reasoning, 语言理解, Comprehension, 指令遵循, Instruction Following, 不支持, Unsupported
Openness: open
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

Original evidence https://hub.opencompass.org.cn/dataset-detail/S1-Bench

S1-Bench paper, code and dataset

Paper https://arxiv.org/abs/2504.10368
Code https://github.com/WYRipple/S1_Bench
Dataset https://huggingface.co/datasets/WYRipple/S1-Bench

No reported scores are on record for this benchmark yet.

Which sources cite S1-Bench?

S1-Bench

Related 强推理, Strong Reasoning, 理解, Understanding, 指令跟随, Instruct, 系统1, 快思考, LRM, 大语言模型, LLM, 逻辑推理, Reasoning, 语言理解, Comprehension, 指令遵循, Instruction Following, 不支持, Unsupported benchmarks