Model Evaluation blog posts

Vibe-Checking Qwen3.8-Max on Hard Visual Grounding Tasks

Your segmentation model is great at livers and terrible at pancreases

Exploring the PointMotionBench Benchmark in FiftyOne

How FiftyOne's Model Evaluation Helped Me Reduce False Positives by 70.9% Without Retraining

Rethinking How We Evaluate Multimodal AI

Unified Model Insights with FiftyOne Model Evaluation Workflows

This Visual Illusions Benchmark Makes Me Question the Power of VLMs

Memes Are the VLM Benchmark We Deserve

AIMv2 Outperforms CLIP on Synthetic Dataset ImageNet-D

ImageNet-D: New Synthetic Test Set Designed to Rigorously Evaluate the Robustness of Neural Networks

Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation

Best Practices for AI Model Evaluation