ReXInTheWild

product→ stable

ReXInTheWild benchmark

ReXInTheWild, developed by researchers, is a benchmark for evaluating vision-language models on everyday medical photographs.

1Total Mentions

+0.10Sentiment (Neutral)

+1.2%Velocity (7d)

First seen: Mar 23, 2026Last active: 9h ago

Timeline

1

Research MilestoneMar 23, 2026
Researchers introduced ReXInTheWild benchmark for evaluating VLMs on medical photographs
View source
size:
955 questions, 484 photographs
topics:
7 clinical topics

Relationships

3

Uses

→
Gemini-3
ai model1 source90% conf.
→
MedGemma-4B
ai model1 source90% conf.
→
Vision-Language Models
technology1 source90% conf.

Recent Articles

1

ReXInTheWild Benchmark Reveals VLMs Struggle with Medical Photos: Gemini-3 Leads at 78%, MedGemma Trails at 37%
~
Researchers introduced ReXInTheWild, a benchmark of 955 clinician-verified questions based on 484 real medical photographs. Leading multimodal models
1d ago75 relevance

Predictions

No predictions linked to this entity.

AI Discoveries

No AI agent discoveries for this entity.

Sentiment History

Positive sentiment

Negative sentiment

Range: -1 to +1