• 4 min read
Cosmos 3: Evaluation for Vision Use Cases
NVIDIA Cosmos 3 offers zero-shot performance on fixed-camera footage across airports, warehouses, and production lines.
Blog
Erik Kokalj
Developer Experience @ Roboflow
Latest Posts by Erik Kokalj
• 6 min read
Gemini 3.5 Flash for Vision: Evaluation and Benchmarks
Google released Gemini 3.5 Flash May 19, 2026 at Google I/O and it is the highest performing frontier model on the Roboflow Vision Evals leaderboard, beating Gemini 3.1 Pro on counting and spatial reasoning while running about three times faster.
Six months after Gemini 3 Pro set
• 4 min read
Serverless GPU Inference Cost Comparison: Roboflow, GCP, AWS, Azure
In this blog post, we will explore how different cloud providers compare in running custom vision model inference.
Custom RF-DETR Model
If you need OCR, face detection/comparison, or general-purpose COCO-20 classification and detection, the major clouds already offer plenty of managed options, such as AWS Rekognition, GCP Vision, and
• 5 min read
Which is the Best Coding Agent for Vision tasks?
Coding agents are quickly becoming the popular way to build applications, as they generate code, run it, debug errors, and iterate autonomously.
But how well do they perform on tasks related to visual understanding and vision applications? We evaluated the top 4 coding agents (claude code, gemini-cli, openai codex, Cursor)
• 1 min read
Launch: Workflows Builder 2.0
Workflows Builder 2.0 is here with a drag-to-connect interface that makes building and understanding computer vision pipelines faster and clearer.
• 4 min read
Building an AI-powered Bot to Beat the Chrome Dino Game
In this blog post, I'll go through how I created a Bot that uses AI object detection model to beat the Chrome Dino game!
You can also try it out directly by following the README on the GitHub repo.
If someone prefers a video tutorial, you can watch
• 4 min read
Train a YOLO26 Instance Segmentation Model with Custom Data
In this guide, we will demonstrate how to implement instance segmentation using the YOLO26 architecture. To follow along, we recommend opening the YOLO26 Instance Segmentation Colab Notebook.
While object detection tells you where an object is with a box, instance segmentation takes it a step further by identifying the exact
• 4 min read
How to Train a YOLO26 Object Detection Model with Custom Data
In this tutorial, we walkthrough how to train YOLO26 for object detection on a custom dataset.
We recommend working through this blog post side-by-side with the YOLO26 Object Detection Colab notebook. You'll learn how to train a custom model to detect NBA players, referees, and basketballs.
⚡RF-DETR Neural
Stay Connected