Where2Place
Cosmos3-Nano 64% leads since May 2026 100 cluttered real photos with free-space placement instructions. The model points, scored correct if inside the ground-truth mask.
Only 100 images, so gaps under ~10 points are noise. Scoring varies by source (single vs several points, thinking on/off).
- Made by
- University of Washington + NVIDIA (RoboPoint)
- Released
- June 2024
- Kind
- Embodied reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Last in a system card
- May 2026
- Last model added
- May 2026
Cosmos3-Nano leads with 64% among models released by July 2026
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.
The newest model with a score here came out in July 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Cosmos3-Nano 64%
- 2 gemini-robotics-er-1.5-preview 59%
- 3 Cosmos3-Edge 55%
- 4 Gemini Robotics-ER 45%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Cosmos3-Nano | 64% | May 2026 | Lab model card | |
| 2 | gemini-robotics-er-1.5-preview | 59% | Sep 2025 | Lab model card | |
| 3 | Cosmos3-Edge | 55% | May 2026 | Lab model card | |
| 4 | Gemini Robotics-ER | 45% | Mar 2025 | Lab model card |
3 models have held number one in labs’ own numbers since its release in June 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 2 labs
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 |
|---|---|---|---|---|
| May 31, 2026 | Cosmos3-Nano technical report | 64 | Where2Place, Cosmos3-Nano 8B column, Table 10 | Capabilities |
| May 31, 2026 | Cosmos3-Edge technical report | 55 | Where2Place, Cosmos3-Edge 2B column, Table 10 | Capabilities |
| Sep 25, 2025 | gemini-robotics-er-1.5-preview technical report | 59 | Where2Place (Table 19, thinking on). Thinking off 48.0 | Capabilities |
| Mar 25, 2025 | Gemini Robotics-ER technical report | 45 | Where2Place, 2D pointing accuracy (Table 3) | Capabilities |
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%