Skip to content
View original post on X: elvisX· 36/100AI score36/100

Glimpse, a new visual model, scores 8/10 on board-reading test vs 5/10 for Gemini 3.8 Flash

AISummary

Elorian AI releases Glimpse, its first vision-language model, which its founders say led work at Google on Gemini and at Apple on MM-1. In a 10-image test of game boards from an overhead camera, the post says Glimpse read 8 boards fully correctly against 5 for Gemini 3.8 Flash, with results hand-checked.

Post on XView on X
elvisVerified on X
@omarsar0

Pay attention to this new wave of VLMs.

Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1.

Quick test: 10 game boards from an overhead camera. Same prompt, same image, two models, hand-checked.

Glimpse: 8/10 boards fully correct.
Gemini 3.8 Flash: 5/10.

This is what data labeling looks like. Getting the whole frame right, not just most of it, turns raw robot footage into training data.

This is powerful Visual Thinking, not just visual recognition translated into text.

Andrew M. Dai@AndrewDai
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.
View quoted post on X

Source: elvis · x.comPublished

Topics

Multimodal AIData & trainingEvals & benchmarks