Roboflow

@roboflow

Build & use computer vision models fast ✨ Get started: roboflow.com Open source datasets & models universe.roboflow.com

roboflow.com

Joined June 2019

Following

13.9K

Followers

Affiliates Replies Media

Roboflow
@roboflow
Aug 6
our deep dive on qwen3.8-max lots of examples and breakdowns by each category we eval, it's a top choice for vision tasks. we will eval open weights when they arrive we also added muse spark 1.2 and meta is a top vision model provider now. three way race between google, meta,
SkalskiP
@skalskip92
Aug 6
Qwen3.8-Max blogpost - object detection (taxt and box prompts) - object counting - image reasoning - data extraction - cost and speed link: blog.roboflow.com/qwen3-8-max/ tl;dr below Qwen3.8-Max tops our object detection benchmark. it performs well across satellite images,
Roboflow
@roboflow
Aug 5
frontier models are handling more and more complex tasks without fine-tuning models like qwen-3.8 are shifting the ROI curve massively cost dropping and intelligence rising means many new use cases are now possible both technically and financially
SkalskiP
@skalskip92
Aug 5
image reasoning means understanding the objects, text, and relationships in an image to make a decision check out what tasks can you automate with Qwen3.8-Max task: make sure medication is prepared according to the schedule Qwen3.8-Max vs other models: playground.roboflow.com/share/194672b1…
Roboflow
@roboflow
Aug 4
vision evals leaderboard looks totally different from 30 days ago 3 new frontier models from 3 different labs now beat Fable 5, openai is barely in top 10 tradeoffs here to make between speed, cost, open/closed, etc. starting to see models diverge for specific use cases and
Roboflow
@roboflow
Jul 2
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
Roboflow
@roboflow
Aug 3
big breakthrough: qwen3.8-max is now the top of our object detection leaderboard if the latency works for your use case, this is for sure the top model more to come as we continue to learn more about the model
SkalskiP
@skalskip92
Aug 3
Qwen3.8-Max is the best object detection VLM - satellite images - infrared images - documents - techical drawings - hand-sketched diagrams - crowded scenes - small objects ↓ check out some of those insane examples
Roboflow
@roboflow
Jul 30
pretty clear at this point what model you should use to automate labeling vision data
SkalskiP
@skalskip92
Jul 30
“why use VLMs for open-vocabulary detection? YOLO-E also supports text prompts and runs in real time.” true. but text prompting is not the same as language understanding using the same class names as for VLMs, YOLOE-26x scored 20.2% mAP@50 and YOLOE-11l scored 18.3% prompts