3DSRBench
SenseNova-SI-1.3-InternVL3-8B 62.4% leads since January 2026 Models answer questions about 3D spatial relations in images, such as height, location, orientation and relations between objects.
Results are often reported under a circular evaluation setting.
- Made by
- Wufei Ma, Alan Yuille et al.
- Released
- December 2024
- Kind
- Spatial reasoning and counting
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Strongest model tested
- GPT-4o mini #177 on the capability index
- Last in a launch post
- January 2026, dropped before it saturated
- Last model added
- January 2026
- Scores refreshed
- November 12th, 2026
In the authors’ words
3D spatial reasoning is the ability to analyze and interpret the positions, orientations, and spatial relationships of objects within the 3D space. This allows models to develop a comprehensive understanding of the 3D scene, enabling their applicability to a broader range of areas, such as autonomous navigation, robotics, and AR/VR. While large multi-modal models (LMMs) have achieved remarkable progress in a wide range of image and video understanding tasks, their capabilities to perform 3D spatial reasoning on diverse natural images are less studied. In this work we present the first comprehensive 3D spatial reasoning benchmark, 3DSRBench, with 2,772 manually annotated visual question-answer pairs across 12 question types. We conduct robust and thorough evaluation of 3D spatial reasoning abilities by balancing data distribution and adopting a novel FlipEval strategy. To further study the robustness of 3D spatial reasoning w.r.t. camera 3D viewpoints, our 3DSRBench includes two subsets with 3D spatial reasoning questions on paired images with common and uncommon viewpoints. We benchmark a wide range of open-sourced and proprietary LMMs, uncovering their limitations in various aspects of 3D awareness, such as height, orientation, location, and multi-object reasoning, as well as their degraded performance on images from uncommon 6D viewpoints. Our 3DSRBench provide valuable findings and insights about future development of LMMs with strong spatial reasoning abilities. Our project page is available at https://3dsrbench.github.io/.
SenseNova-SI-1.3-InternVL3-8B leads with 62.4%
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.
llama3-llava-next-8b leads with 49.6% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
SenseNova-SI-1.3-InternVL3-8B leads with 62.4%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
Source: Labs’ model cards
- 1 llama3-llava-next-8b 49.6%
- 2
Cambrian-1-8B 44.1% - 3 GPT-4o mini 39.1%
- 4 llava-v1.5-7b 36.8%
Source: Official 3DSRBench leaderboard
- 1 SenseNova-SI-1.3-InternVL3-8B 62.4%
- 2 llama3-llava-next-8b 49.6%
- 3 Cambrian-1-8B 44.1%
- 4 GPT-4o mini 39.1%
- 5 llava-v1.5-7b 36.8%
Sources: Labs’ model cards and official 3DSRBench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SenseNova-SI-1.3-InternVL3-8B | 62.4% | Jan 2026 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | llama3-llava-next-8b | 49.6% | Apr 2024 | Official leaderboard | |
| 2 | Cambrian-1-8B | 44.1% | Jun 2024 | Official leaderboard | |
| 3 | GPT-4o mini | 39.1% | Jul 2024 | Official leaderboard | |
| 4 | llava-v1.5-7b | 36.8% | Oct 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SenseNova-SI-1.3-InternVL3-8B | 62.4% | Jan 2026 | Lab model card | |
| 2 | llama3-llava-next-8b | 49.6% | Apr 2024 | Official leaderboard | |
| 3 | Cambrian-1-8B | 44.1% | Jun 2024 | Official leaderboard | |
| 4 | GPT-4o mini | 39.1% | Jul 2024 | Official leaderboard | |
| 5 | llava-v1.5-7b | 36.8% | Oct 2023 | Official leaderboard |
The benchmark's own leaderboard has 8 entries, 4 of them models we track. Switch the scores above to rank them together.
Number one over time Number one over time 2 models have held number one with claims included since its release in December 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official 3DSRBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official 3DSRBench leaderboard and labs’ model cards
Labs headline it less often now, last in January 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 |
|---|---|---|---|
| Jan 8, 2026 | SenseNova-SI-1.3-InternVL3-8B | 62.4 | 3DSRBench |
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%