OmniSpatial
Nemotron 3.5 Super VL 58.6% leads since October 2026 Nemotron 3.5 Super VL 58.6% leads since October 2026 Vision language models answer over 8,400 spatial reasoning questions in four groups: dynamic reasoning, complex spatial logic, spatial interaction and perspective taking.
Questions are manually annotated and span 50 subcategories grounded in cognitive psychology.
- Made by
- Jia, Qi et al. (OmniSpatial authors)
- Released
- June 2025
- Kind
- Spatial reasoning and counting
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Strongest model tested
- o3 #83 on the capability index
- Last in a launch post
- December 2025, dropped before it saturated
- Last model added
- October 2026
- Scores refreshed
- November 12th, 2026
In the authors’ words
Spatial reasoning is a key aspect of cognitive psychology and remains a bottleneck for current vision-language models (VLMs). While extensive research has aimed to evaluate or improve VLMs' understanding of basic spatial relations, such as distinguishing left from right, near from far, and object counting, these tasks cover only the most elementary layer of spatial reasoning and are largely approaching saturation in the latest reasoning models. In this work, we introduce OmniSpatial, a comprehensive and challenging benchmark for spatial reasoning, grounded in cognitive psychology. OmniSpatial covers four major categories: dynamic reasoning, complex spatial logic, spatial interaction, and perspective-taking, with 50 fine-grained subcategories. Through careful manual annotation, we construct over 8.4K question-answer pairs. Extensive experiments show that both open- and closed-source VLMs exhibit significant limitations in comprehensive spatial reasoning. We also explore two strategies-PointGraph (explicit scene graph cues) and SpatialCoT (novel-view chain-of-thought)-to bolster spatial reasoning.
Nemotron 3.5 Super VL leads with 58.6%
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.
o3 leads with 56.3% 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.
Nemotron 3.5 Super VL leads with 58.6%, 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.
- 1 Nemotron 3.5 Super VL 58.6%
- 2 GLM-4.6V 52%
- 3
InternVL3.5-241B-A28B 51.9% - 4
STEP3-VL-10B 51.6% - 5 GLM-4.5V 51%
- 6 GLM-4.1V-9B-Thinking 47.7%
Source: Labs’ model cards
- 1 Nemotron 3.5 Super VL 58.6%
- 2 o3 56.3%
- 3 GLM-4.6V 52%
- 4 InternVL3.5-241B-A28B 51.9%
- 5 STEP3-VL-10B 51.6%
- 6 GLM-4.5V 51%
- 7 GLM-4.1V-9B-Thinking 47.7%
Sources: Labs’ model cards and official OmniSpatial leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nemotron 3.5 Super VL | 58.6% | Oct 2026 | Lab model card | |
| 2 | GLM-4.6V | 52% | Dec 2025 | Lab model card | |
| 3 | InternVL3.5-241B-A28B | 51.9% | Aug 2025 | Lab model card | |
| 4 | STEP3-VL-10B | 51.6% | Jan 2026 | Lab model card | |
| 5 | GLM-4.5V | 51% | Aug 2025 | Lab model card | |
| 6 | GLM-4.1V-9B-Thinking | 47.7% | Jul 2025 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o3 | 56.3% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nemotron 3.5 Super VL | 58.6% | Oct 2026 | Lab model card | |
| 2 | o3 | 56.3% | Apr 2025 | Official leaderboard | |
| 3 | GLM-4.6V | 52% | Dec 2025 | Lab model card | |
| 4 | InternVL3.5-241B-A28B | 51.9% | Aug 2025 | Lab model card | |
| 5 | STEP3-VL-10B | 51.6% | Jan 2026 | Lab model card | |
| 6 | GLM-4.5V | 51% | Aug 2025 | Lab model card | |
| 7 | GLM-4.1V-9B-Thinking | 47.7% | Jul 2025 | Lab model card |
The benchmark's own leaderboard has 3 entries, 1 of them models we track. Switch the scores above to rank them together.
5 models have held number one in labs’ own numbers since its release in June 2025 Number one over time 2 models have held number one with claims included since its release in June 2025
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.
Sources: Official OmniSpatial leaderboard and labs’ model cards
Labs headline it less often now, last in December 2025
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 |
|---|---|---|---|
| Dec 8, 2025 | GLM-4.6V | 52 | OmniSpatial |
| Aug 25, 2025 | InternVL3.5-241B-A28B | 51.9 | OmniSpatial |
| Aug 11, 2025 | GLM-4.5V | 51 | OmniSpatial |
6 system cards report it, from 4 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 |
|---|---|---|---|---|
| Oct 15, 2026 | Nemotron 3.5 Super VL technical report | 58.6 | OmniSpatial, SpatialClaw harness, with agentic vision training, Table 7 | Capabilities |
| Jan 14, 2026 | STEP3-VL-10B technical report | 51.6 | OmniSpatial, SeRe (Tables 1 and 3). PaCoRe 52.58 | Capabilities |
| Jan 1, 2026 | GLM-4.6V technical report | 52 | OmniSpatial, GLM-4.6V thinking (Table 2) | Capabilities |
| Aug 25, 2025 | InternVL3.5-241B-A28B technical report | 51.9 | OmniSpatial (Table 2, Table 11) | Capabilities |
| Aug 13, 2025 | GLM-4.5V technical report | 51 | OmniSpatial, GLM-4.5V thinking (Table 2) | Capabilities |
| Jul 1, 2025 | GLM-4.1V-9B-Thinking technical report | 47.7 | OmniSpatial, GLM-4.1V-9B-Thinking thinking (Table 2) | 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%