MedCTA: A Benchmark for Clinical Tool Agents

MedCTA is a benchmark dataset for evaluating clinical tool agents, created by IVUL-KAUST. Each example contains a clinical image, a user query, a reference tool-use trajectory, and a ground-truth answer. The dataset was last updated on May 24, 2026.

Use Cases

• Benchmarking agent performance on multimodal clinical reasoning based on images and queries
• Training AI models to follow tool-use trajectories in medical settings
• Evaluating the ability of agents to observe, reason, and answer in clinical contexts

Strengths

• Provides a structured benchmark with ground-truth answers for evaluation
• Includes multimodal elements (clinical images and text queries) as described

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 is unknown, which may limit suitability assessment

Provenance

Source

IVUL-KAUST

Freshness

Last updated 2026-05-24 07:11:29; freshness should be verified