Roboflow

Build & use computer vision models fast ✨

Get started: source datasets & models

[Roboflow @roboflow]

@sharps_research @ultralytics here's our free and open research that is helping decelerate AI by giving everyone SOTA performance for free

https://t.co/zqjmcmSII6

please read it and slow yourself down

[Roboflow @roboflow]

@mattvanswol 💜

[Roboflow @roboflow]

@manaspgandhi incoming

[Roboflow @roboflow]

@sponsorlytix agreed!

[Roboflow @roboflow]

looks like grok is entering the vision arena soon

cool to see elon in the weeds on that

[SkalskiP @skalskip92]

GPT 5.6 Sol is the best "vision" model OpenAI ever released

massive gains in object detection and counting.

still very strong in OCR

↓ deep GPT 5.6 dive

[Roboflow @roboflow]

related?

https://t.co/53vbVqWl8J

[Techmeme @Techmeme]

Sources: Cursor is building a general-purpose AI agent codenamed Sand, aimed at non-developers, that handles emails, texts, and documents to rival Claude Cowork (@graceihle / The Information)

(Visit Techmeme dot com for the link and full context!)

[Roboflow @roboflow]

@menrva33 so so so cool. thank you for building and sharing

[Roboflow @roboflow]

@zachlieberman 💯

[Roboflow @roboflow]

@mcsaritekin Let us fix it first

[SkalskiP @skalskip92]

object counting is one of the most popular use cases for VLMs

what previously required training a model on a custom dataset now fits into a prompt

quality control, inventory checks, shelf monitoring

check how different VLMs handle object counting: https://t.co/OTrn9gP4Mj

[SkalskiP @skalskip92]

I’m evaluating fable 5 on object detection, but so far it performs much worse than gemini 3.5 flash

any tips?

it struggles with cluttered scenes and overlapping objects

try gemini 3.5 flash vs fable 5 for free: https://t.co/8xnioJ6HkG

↓ some positive fable 5 examples

[Roboflow @roboflow]

very good thread with sample data showing Fable 5 performance against other models for vision tasks

important to see the types of tasks frontier models can/cant do

will give you ideas for how to use them successfully in production

[SkalskiP @skalskip92]

need a model for OCR and VQA? Fable 5 is NOT your best option

Gemini 3.5 Flash is 1.3x faster, 2.9x cheaper, and more accurate

Fable 5 struggles especially on tasks that require counting objects.

↓ cost comparison and interesting failure cases

[Roboflow @roboflow]

@Alex_Kedra can confirm the hiring manager has seen this

[Roboflow @roboflow]

@leon_cvetkovski 3.5 35B is the #2 model, we tested the 3.6 version and it didn't improve results

[Roboflow @roboflow]

Fable 5 is back and tied as a top vision model, Sonnet 5 is outside the top 10

Fable 5 is ~3x slower and ~10x more expensive than Gemini 3.5 though

If you're set on Anthropic models, it's the best one for vision

The delta between Sonnet 5 and Fable 5 is really large, Sonnet 5 is slightly worse than Qwen 3.5 9B

but very fast if you're looking for speed!

[Roboflow @roboflow]

You can now build vision applications with Fable 5 in Roboflow

Fable 5 is the best Anthropic model for visual understanding, beating Opus 4.8 on our evals

very high object understanding capability means it's a great option when using a VLM as a judge in your pipeline

ideal for a final step in a process that requires judgement or interpretation of a situation

of course, nails most document, label extraction, ocr, scene reports, etc that you expect of a large frontier model

[Roboflow @roboflow]

link to run your own images against all threes models to see how they compare

https://t.co/FoCE9OyHYl

[Roboflow @roboflow]

every legacy vision product/system/company can probably be built with open source tools and models at this point

and then putting them in production is 100x cheaper than it's ever been

vision is no longer cost prohibitive to build and deploy

[mirrash.eth 🦇🔊 @mirrash7]

I rebuilt FIFA's VAR offside tech run on a single camera for about $2 a match 📈

-Find pitch lines + vanishing point- HSV color matching
-Find players - RF-DETR
-Recreate the moment in 3D - SAM3D Body + 3js

[Roboflow @roboflow]

leaderboard here https://t.co/F8O0nmU2CU

[Roboflow @roboflow]

We added video understanding and Gemini 3.5 Flash wins there as well

Seems like the all around best frontier vision model

If you're starting to build vision apps, use Gemini 3.5 Flash to prototype

You can quickly build a work pipeline across different use cases and types of data, then move to a fine-tuned model as you scale up

Expanding the video benchmark soon, just getting started

[Roboflow @roboflow]

we saw the same thing with our vision leaderboard

still testing and wrapping our heads around Gemini 3.5 Flash but it feels like a pivotal shift in frontier models

way cheaper and way faster than anything else, and performance is super high

first time it feels like you can really use a VLM for high scale tasks. lots of previous tasks that required making workflows of smaller, cheaper models now looks possible (speed and cost wise) with Gemini 3.5 Flash

a few examples below