Datasets › SAS-Bench
SAS-Bench
SAS-Bench represents the first specialized benchmark for evaluating Large Language Models (LLMs) on Short Answer Scoring (SAS) tasks. Utilizing authentic questions from China's National College Entrance Examination (Gaokao), our benchmark offers:
- 1,030 questions spanning 9 academic disciplines
- 4,109 expert-annotated student responses
- Step-wise scoring with Step-wise error analysis
- Multi-dimensional evaluation (holistic scoring, step-wise scoring, and error diagnosis consistency)
Benchmarks archive 2025-07-28
No leaderboard in the archive resolves to this dataset.
Papers archive 2025-07-28
No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
No modality tagged.
Languages archive 2025-07-28
Variants archive 2025-07-28
- SAS-Bench
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections