Roboflow (@roboflow) header
Roboflow (@roboflow) profile picture

Turn images, videos, and streams into intelligence

Joined June 2019
Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)Photo by Roboflow (@roboflow)
Roboflow retweeted
GPT-6.2 is getting roasted on X meanwhile, Astra and Sol just took #1 and #2 on my object detection benchmark so I have some awkwardly positive results to share ↓ benchmarks and examples
I will not be writing a full review of GPT-6.2 Astra / Sol. I had a terrible experience testing them. They were essentially unusable. I do not recommend these models.
40
41
8
911
108,980
It’s pretty wild to take a step back and see how much @roboflow changed in a year. @braddwyer put together a great recap of what we shipped. And we got a lot more cool stuff in the works. youtube.com/watch?v=GLqemlJa…
1
4
399
Gemini 4 Carbon is now the top overall vision model on our benchmarks Text/OCR seems to be a consistent high performing area over others - text localization and recognition: finding text, drawing boxes, and reading it - short string extraction: reading a specific value from an image - long text transcription: reading full passages from images Beyond that, it's #1 in core vision tasks like object detection and reasoning. Disclaimer: it is the slowest and most expensive of the top models so if you need cost/speed, this one isn't for you
Gemini 4 Carbon is so fucking good at computer vision - #1 overall - #2 object detection - #1 short string extraction - #4 structured JSON extraction - #1 long text transcription - #1 text localization and recognition very slow and expensive though... ↓ examples
6
8
1
59
4,573
I fine-tuned V-JEPA 2.1 on 25 clips to learn the steps of an F1 pit stop 🏎️ • V-JEPA 2.1 (ViT-B), 384 px, fine-tuned on @roboflow • Per-frame head: which steps are active + how far each extends • 64 frames at a time (6.4 s at 10 fps) • ~2 h to train A detector can't do this robustly: wheel on and wheel off look the same in a still. The model has to see the motion.
3
5
85
4,990
Roboflow retweeted
We are releasing a new package from @roboflow, meet reid! It turns a crop of an object into an embedding, so you can tell objects apart, like this player across clips of a game. Can't wait to see what you build with it! github.com/roboflow/re-ID
20
85
4
1,132
64,423
Roboflow retweeted
Re-Identification available in @roboflow Trackers! Until now, when a player left the frame and came back, the tracker gave them a new ID. Re-ID fixes that by comparing how players look, and it's now integrated in trackers v2.7.0. The models come from our new open-source package reid, which also works on its own. pip install "trackers[reid]" and start using it!
16
22
1
201
7,307
Today we’re announcing that we’ve partnered with NVIDIA and joined the Cosmos Coalition, a global initiative among leading AI labs, as a premiere provider of multi-modal data and post-training capabilities that advance frontier world model research. We believe the next wave of the AI boom will be defined by what intelligence can do in the physical economy, and that vision is the bottleneck to unblock.
5
4
72
4,478
NVIDIA introduced the coalition in May 2026 to bring model builders, developers, and organizations building physical AI together around open world models. The effort supports collaboration on models, research, and evaluation methods to advance systems that can understand and simulate the physical world. More info: roboflow.com/blog/roboflow-j…
1
1
5
976
Joining the coalition places Roboflow Labs’ work within a shared effort to advance those capabilities. We see an opportunity to connect progress in frontier models with the breadth of tasks developers face outside the lab, and to help turn that progress into tools people can build with. Roboflow Labs draws on what the 2M+ developers and Fortune 500 enterprises building on Roboflow are actually trying to solve. That real-world task distribution shapes the research, benchmarks like RF100-VL, and data we bring to model builders. More on Roboflow Labs: labs.roboflow.com/
2
300
Roboflow retweeted
GPT-6.1 Terra beats Astra in our vision benchmarks wtf OpenAI? had to double-check the results - text - object detection - counting also ~47% faster and ~92% cheaper ↓ leaderboards and examples
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
66
57
34
1,060
100,518
Roboflow retweeted
We are hosting the Visual Intelligence Summit on October 22 in SF. The physical world is AI's biggest opportunity and the best way to advance humanity in our lifetimes. Few people are building for AI beyond the screen. The Summit is for the people who see it differently and want to be at the frontier of bringing AI into the physical world. If you’re building for that future, join us.
7
16
10
63
65,036
Roboflow retweeted
Ever wanted to know if you're cooked in an IRL game of chess? 💀 So I built Stockfish IRL. A camera watches a real board, tracks every move, and literally yells at you when you blunder. Built with @roboflow 👇
3
1
13
1,140
livestream today sharing all the findings we have on using Argon for vision TLDR: Google is back. Argon tops almost everything. Argon is good enough that we started testing it on new areas where most VLMs aren't usable like segmentation, keypoints, and video reasoning Exciting to have a model this good. Never been a better time to build with vision Also, models hitting 90% on our evals means we are going to invest in expanding benchmarks. Stay tuned!
Gemini 4 Argon stream in 30 minutes. see you!
2
31
2,617
Roboflow retweeted
Gemini 4 Argon vs GPT-6 Astra YouTube stream tomorrow, Oct 15th, 8 AM PT / 11 AM ET / 5 PM CET save the time and see you tomorrow - detection - segmentation - transcription - data extraction - efficiency and cost what else? link: youtube.com/live/bBX_c5AFuMQ
Astra dethroned Gemini 4 Argon is the best "vision" model #1 for detection: - tight, precise boxes - dense scenes #1 for text extraction: - small text - handwritten text - complex tables - rotated text 4× cheaper than Astra at high
3
3
1
76
5,546
Gemini 4 Argon expands what’s possible in computer vision As models improve, your apps should too Routing tasks to the right frontier or specialized model is how you can build production systems that scale with your accuracy, speed, and cost needs Can't wait to see all the new products people ship with this one
Astra dethroned Gemini 4 Argon is the best "vision" model #1 for detection: - tight, precise boxes - dense scenes #1 for text extraction: - small text - handwritten text - complex tables - rotated text 4× cheaper than Astra at high
4
3
61
3,433