Elorian launches Glimpse, a visual thinking model it says rivals GPT 6 Astra on visual reasoning benchmarks
Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that. Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.
Context
Models that can follow objects through video and changing angles are needed for robotics and video work, and a small team claiming frontier results would be notable.
This is a first hand launch post from Andrew Dai, Elorian's cofounder and CEO and a former Google DeepMind researcher. The comparisons with GPT 6 Astra come from the company's own benchmark choices.
Deep dive
On October 16, Andrew Dai posted that he spent years watching models ace a single image and completely miss anything that moves or changes angle, and that Elorian was fixing that. He invited people to try Glimpse, its first visual thinking model, with what he called competitive frontier performance compared to Astra on key public visual reasoning benchmarks.
Elorian's blog describes Glimpse as a model that reasons about the physical world from what it sees, following objects in motion and across viewpoints and connecting observations to what happens next. It says Glimpse matches and sometimes exceeds GPT 6 Astra and Claude Opus 5.5 on multimodal benchmarks while being much smaller and cheaper, and that a small team built it with only a few hundred GPUs by post training an open weights base model. It is available through an API and a chat interface.
The company says robot control and calibrated scene reconstruction remain future work. Reports describe Elorian as a Palo Alto startup founded in 2025 by Dai, Yinfei Yang and Seth Neel, with researchers from Google DeepMind and Apple.
What to expect next
Watch independent tests of Glimpse on video and multi view reasoning against GPT 6 Astra, Gemini and Claude, beyond the benchmarks Elorian chose.
Also watch pricing and adoption of its API, which open weights base model it builds on, and whether Elorian moves toward the robotics and action models its blog describes as the next step. Funding news would also show investor appetite for this approach.