Unverified50% confidenceReleaseExact time
The researchers open-sourced MedPhysBench's code, per-problem results, and targeted test responses.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedThe research team released an accompanying benchmark dataset, SkillCascade-Bench.73% similarUnverifiedMedPhysBench's error-correction task shows the model a colleague's full worksheet or only the final result, with half correct and half containing a single implanted error, thereby testing the model's ability to find errors.72% similarUnverifiedMedPhysBench contains ten seeded generators for producing calculation problems, reference answers are generated by code implementing the relevant protocols, and the scorer handles unit conversion and applies tolerance intervals.71% similarUnverifiedMedPhysBench is a benchmark for systematically evaluating the reliability of language models on medical physics calculation and error-correction tasks, covering four major domains: radiation therapy, diagnostic imaging, nuclear medicine, and radiation protection.70% similarUnverifiedThe researchers developed TrialScribe, a domain-specific agent framework that equips coding agents with task skills and a verification loop.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134266API
curl https://kongchang.com/api/v1/knowledge/claims/1134266MCP
get_claim(id=1134266)