Zero-shot evaluation of open vision-language models as System 1 decision models on radiology tasks

arXiv:2611.01631 · cs.CV, cs.AI · Submitted 2026-11-01 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-11-01

Updated: 2026-11-14

Comments: 26 pages, 4 tables, 2 figures. v2: added Gemma 4 31B and MedGemma 1.5 4B to the comparison

Code: https://github.com/slowvak/System1Benchmark

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers