A Chinese medical benchmark dataset published in August 2023 by FreedomIntelligence. It is designed for evaluating AI models on medical knowledge and clinical reasoning tasks. The dataset includes an exam test component, with answers disclosed in January 2024.
Use Cases
- Benchmarking AI model performance on Chinese medical knowledge based on the described exam test.
- Evaluating clinical reasoning capabilities of language models using the disclosed test answers.
- Training or fine-tuning models for medical question answering tasks in Chinese.
Strengths
- Includes a dedicated exam test component for structured evaluation.
- Answers to the exam test have been disclosed to facilitate testing.
- Managed by an organization (FreedomIntelligence) with a track record of updates, including a fix in February 2024.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count and dataset size are unknown, which may limit suitability assessment.
Provenance
- Source
- FreedomIntelligence
- Freshness
- Last updated 2024-04-05 16:10:47; freshness should be verified.