SUNRGBD
Gemini Robotics-ER 48.3 leads since March 2025 Models detect objects in about 10,000 indoor RGB-D images and predict their 3D bounding boxes. Scored by average precision.
- Made by
- Princeton University
- Released
- June 2015
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Strongest model tested
-
Qwen3.5 397B-A17B #77 on the capability index - Last in a launch post
- March 2026, dropped before it saturated
- Last model added
- March 2026
Gemini Robotics-ER leads with 48.3 among models released by February 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 February 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 Gemini Robotics-ER 48.3
- 2 Qwen3.5 397B-A17B 38.3
- 3 Qwen3.5-122B-A10B 36.2
- 4 Qwen3.5-27B 35.4
- 5 Qwen3-VL-235B-A22B 34.9
- 6 Qwen3.5-35B-A3B 33.4
- 7
Seed1.5-VL 32.0 - 8 Qwen3.5-2B 28.7
- 9 Qwen3.5-0.8B 26.1
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini Robotics-ER | 48.3 | Mar 2025 | Lab model card | |
| 2 | Qwen3.5 397B-A17B | 38.3 | Feb 2026 | Lab model card | |
| 3 | Qwen3.5-122B-A10B | 36.2 | Feb 2026 | Lab model card | |
| 4 | Qwen3.5-27B | 35.4 | Feb 2026 | Lab model card | |
| 5 | Qwen3-VL-235B-A22B | 34.9 | Sep 2025 | Lab model card | |
| 6 | Qwen3.5-35B-A3B | 33.4 | Feb 2026 | Lab model card | |
| 7 | Seed1.5-VL | 32.0 | May 2025 | Lab model card | |
| 8 | Qwen3.5-2B | 28.7 | Mar 2026 | Lab model card | |
| 9 | Qwen3.5-0.8B | 26.1 | Mar 2026 | Lab model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Gemini Robotics-ER 48.3 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 headline it less often now, last in March 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 |
|---|---|---|---|
| Mar 2, 2026 | Qwen3.5-0.8B | 26.1 | SUNRGBD 26.1/23.3 (with CI / without CI) |
| Mar 2, 2026 | Qwen3.5-2B | 28.7 | SUNRGBD 28.7/25.6 (with CI / without CI) |
| Feb 24, 2026 | Qwen3.5-35B-A3B | 33.4 | SUNRGBD |
| Feb 24, 2026 | Qwen3.5-27B | 35.4 | SUNRGBD |
| Feb 24, 2026 | Qwen3.5-122B-A10B | 36.2 | SUNRGBD |
| Feb 16, 2026 | Qwen3.5 397B-A17B | 38.3 | SUNRGBD |
| Sep 23, 2025 | Qwen3-VL-235B-A22B | 34.9 | SUNRGBD |
3 system cards report it, from 3 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 |
|---|---|---|---|---|
| Nov 26, 2025 | Qwen3-VL-235B-A22B technical report | 34.9 | SUNRGBD, 3D grounding (Table 2) | Capabilities |
| May 11, 2025 | Seed1.5-VL technical report | 32 | SUN-RGBD 3D detection AP@15, thinking, stated in 6.1.2 text. Non-thinking 33.5 | Capabilities |
| Mar 25, 2025 | Gemini Robotics-ER technical report | 48.3 | SUN-RGBD 3D object detection AP@15 (Table 4) | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%