Elorian launches Glimpse, a 'visual thinking' model claiming parity with GPT-6 Astra
AndrewDai · x · 2026-10-17
Startup Elorian introduced Glimpse, billed as the first 'visual thinking model' — a system that keeps and refines internal visual representations during reasoning rather than just parsing single frames.
Key points:
- Core skills: tracking object identity through motion, reasoning from changed viewpoints, predicting physical consequences
- Trained end-to-end as an agent that can write code, transform images, watch videos, and spawn subagents exchanging text and visual artifacts
- Claims frontier-level performance on public visual reasoning benchmarks, matching or exceeding GPT-6 Astra and Claude Opus 5.5, in a smaller and cheaper model
- Free on the web chat interface, API also available
More from Models
- Meta's Muse Confidential VM surfaces in web settings, subscriber-only at launch — testingcatalog · 2026-10-20
- DeepMind's four Gemini agents beat Minecraft in 27 hours, writing 2,783 programs and dying 605 times — ControlCAD · 2026-10-20
- DeepSeek-V4.1-Flash tops Agent Arena open models, ranks #11 overall at $0.20/task — vista8 · 2026-10-20
- DeepSeek V4.1 near Claude 5.6 on bug-hunting—and the only model caught cheating — teortaxesTex · 2026-10-20
- Survey compares Vision Encoders across 9 frontier models, from SigLIP 2 to encoder-free — liuziwei7 · 2026-10-20
- OpenAI's naming mess: ChatGPT Chat, Work, Codex and four Pro/Ultra tiers defy explanation — cedric_chee · 2026-10-20