ASIMOV-Agentic
Only in system cards
Robot reasoning agents decide when to refuse, stop or ask a human. Parts cover safety constraints, people within one meter, safe VLA tool calls, task feasibility and unclear instructions or scenes.
Released with Gemini Robotics 2 on 2026-07-30. The Hugging Face dataset is gated. Gemini 4 Argon safety report gives sub-scores only, with no overall score.
Made by Google DeepMind Released Jul 2026 Embodied reasoning All tasks public Last in a system card Jul 2026
Last model added Jul 2026
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
1
System card reports it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for ASIMOV-Agentic yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 29 Jul 2026 |  Gemini Robotics ER 2 technical report | ASIMOV-Agentic, no overall score: Safety Instruction Following accuracy Text 98.0, Pointing 97.8, BBox 97.8, Tool Use 89.1 (Fig. 3), Safety Tool Calling 100 (2.3), VLA Feasibility one-step 95.8 at DI3 and 62.0 at DI0 (Fig. 10), Instruction Ambiguity 83.8 ambiguous and 88.9 non-ambiguous (Fig. 13), Scene Uncertainty 89.3 uncertainty awareness and 35.5 helpfulness (Fig. 15) | Safety |
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%
- RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate.
GR00T N1.7 8.58% - 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%
- 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%
- LIBERO Fading Simulated Franka tabletop tasks in four 10-task suites. Policies fine-tuned on 50 demos per task. Success rate over ~50 trials.
MolmoAct 2 97.2%