Vendor evaluation scope and example types, not our inference test
Separate runs, reference answers and total task cost →
Not every explanation on the launch page is a Glimpse run.
Elorian · Released 2026-10-16
Glimpse
A visual-reasoning research preview offered through an API and chat. Listed rates are $0.60 per million input tokens and $3 per million output tokens; repeated inspection also takes time and tokens. In the robot example, Glimpse plans and π0.5 executes; this is not direct action generation or our test.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Evaluations: conditions and results
Vendor evaluation · no comparable score in our three current boards
Visual-task results, effort and comparison conditions ↗
How this capability connects to works and uses
Simulation comparison retaining default/high and planning-cost scope
How planners decide the next step for one robot policy →
The robot demo asks when to finish putting cream cheese in a bowl and move on to placing that bowl atop a cabinet.
Original animated input and published model trace
Reinspect two birds in a sub-second transition →
A 6.13-second animation asks for a complete description of two birds’ actions: order, identity and what happens during a camera move.
Published vendor model traces, not our inference test
Rewatching intervals to judge train speed and a camera transition ↗
Vendor demonstration · planning model and execution policy are distinct
High-level planning and checks with the same π0.5 policy ↗
Elorian model evolution
- Glimpse · 研究预览
The API and chat research preview presents visual reinspection, video understanding and high-level robot planning; its vendor tests and examples are separate from our three independent source boards.
Original release ↗