Book a demo Try Voxel51

Model Evaluation blog posts

What Does It Actually Cost to Run an AI Agent? Claude, GPT, and Gemini, Head to Head

by Adonai Vera, DevRel

Model evaluation

•

Sep 22, 2026

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

by Harpreet Sahota, DevRel

Model evaluation

•

Aug 7, 2026

Your segmentation model is great at livers and terrible at pancreases

by Jimmy Guerrero, DevRel

Model evaluation

•

Jul 31, 2026

Exploring the PointMotionBench Benchmark in FiftyOne

by Jimmy Guerrero, DevRel

Model evaluation

•

Jun 22, 2026

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

by Sid Mehta, Customer Success

Model evaluation

•

Mar 30, 2026

Rethinking How We Evaluate Multimodal AI

by Harpreet Sahota, DevRel

Model evaluation, Product and news

•

Jun 12, 2025

Unified Model Insights with FiftyOne Model Evaluation Workflows

by Nick Lotz, DevRel

Model evaluation

•

Apr 11, 2025

This Visual Illusions Benchmark Makes Me Question the Power of VLMs

by Harpreet Sahota, DevRel

Model evaluation

•

Mar 4, 2025

Memes Are the VLM Benchmark We Deserve

by Harpreet Sahota, DevRel

Model evaluation

•

Feb 21, 2025

AIMv2 Outperforms CLIP on Synthetic Dataset ImageNet-D

by Harpreet Sahota, DevRel

Model evaluation

•

Feb 12, 2025

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

by Harpreet Sahota, DevRel

Model evaluation

•

Feb 11, 2025

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

by Paula Ramos, DevRel

Model evaluation

•

Jan 22, 2025

Enough data wrangling. 
Request a demo.

Get started Explore the Demo

© 2026 Voxel51 All Rights Reserved

Terms of Service