GeoMind
Robot agents manipulate tabletop objects using spatial relationships and remembered positions. The benchmark measures success across 54 task variants.
- Made by
- Jinghe Wang and colleagues
- Released
- November 2026
- Kind
- Embodied reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
InternVLA-M1 tops the leaderboard with 26.4% OpenVLA leads with 20.7% among models released by April 2025
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model we track is OpenVLA, at 20.7%. Agents built around a model, such as MOKA + Claude Sonnet 4.6, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 InternVLA-M1 26.4%
- 2 Spatial-Forcing 24%
- 3
OpenVLA 20.7%
- 4 SpatialVLA 18.3%
- 5 MOKA + Claude Sonnet 4.6 16.9%
- 6 COPA + Claude Sonnet 4.6 15.9%
- 7 π0.5 12.5%
- 8 π0 11.3%
- 9 GPT-4o (snapshot unspecified) 11.1%
- 10 COPA + Gemini 2.5 Flash Sep 2025 4.60%
- 11 MOKA + Gemini 2.5 Flash Sep 2025 4.00%
Source: The GeoMind paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | InternVLA-M1 | 26.4% | Official leaderboard | ||
| 2 | Spatial-Forcing | 24% | Official leaderboard | ||
| 3 | | 20.7% | Jun 2024 | Official leaderboard | |
| 4 | SpatialVLA | 18.3% | Official leaderboard | ||
| 5 | MOKA + Claude Sonnet 4.6 | 16.9% | Feb 2026 | Official leaderboard | |
| 6 | COPA + Claude Sonnet 4.6 | 15.9% | Feb 2026 | Official leaderboard | |
| 7 | π0.5 | 12.5% | Apr 2025 | Official leaderboard | |
| 8 | π0 | 11.3% | Oct 2024 | Official leaderboard | |
| 9 | GPT-4o (snapshot unspecified) | 11.1% | COPA | Official leaderboard | |
| 10 | COPA + Gemini 2.5 Flash Sep 2025 | 4.60% | Sep 2025 | Official leaderboard | |
| 11 | MOKA + Gemini 2.5 Flash Sep 2025 | 4.00% | Sep 2025 | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s paper in 2 groups: geomind-base and geomind-aug. Each ranks models on one part of the test. OpenVLA leads 8 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Geometric Inference
3 models we track have a score here.
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The GeoMind paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official GeoMind leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- SimplerEnv In use Real-to-sim replicas of Google Robot and WidowX/Bridge setups. Policies scored by success rate on pick, move, drawer and Bridge tasks. Praxis-1 80%
- RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. Praxis-1 46.2%
- 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 27.6%
- 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%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for π0.5. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (11 entries).
- Pass Models scored 3 models we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for π0.5.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 20.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 7 rows for models we track and 4 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.