Success detection (Google DeepMind)
Embodied reasoning models judge from robot camera images or video whether a manipulation task succeeded. Later versions use raw video to catch mid-execution failures.
Google reports image-based and video-based splits, and earlier single-view and multi-view splits for Gemini Robotics-ER 1.6. Release month is the Gemini Robotics 1.5 era and is likely, not verified.
- Made by
- Google DeepMind
- Released
- September 2025
- Kind
- Embodied reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Kept private
- Last in a launch post
- July 2026, dropped after it saturated
- Last model added
- July 2026
Gemini Robotics-ER 1.6 leads with 90%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1
Gemini Robotics-ER 1.6 90% - 2 Gemini Robotics ER 2 87.7%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini Robotics-ER 1.6 | 90% | Apr 2026 | Lab model card | |
| 2 | Gemini Robotics ER 2 | 87.7% | Jul 2026 | Lab model card |
Google DeepMind’s own number for Gemini Robotics-ER 1.6 passed 85% in April 2026
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs headline it less often now, last in July 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Jul 30, 2026 | Gemini Robotics ER 2 | 87.7 | Success detection (image-based); video-based 82.4 |
| Apr 14, 2026 | Gemini Robotics-ER 1.6 | 90 | Single View Success Detection (multiview 84) |
More in Robotics
- ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy. Gemini Robotics ER 2 78.5%
- RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 29%
- RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. FLUX 3 Action 42.9%
- Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
- Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%
- Moment finding (Google DeepMind) In use Models find the moment in a robot video when an event happens. Scored by accuracy and mean absolute time distance in seconds. Gemini Robotics ER 2 91.3%