OmniSpatial
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.
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.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
GLM-4.6V leads with 52% among models released by Jan 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 Jan 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 GLM-4.6V 52%
- 2
InternVL3.5-241B-A28B 51.9% - 3
STEP3-VL-10B 51.6% - 4 GLM-4.5V 51%
- 5 GLM-4.1V-9B-Thinking 47.7%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GLM-4.6V | 52% | Dec 2025 | Model card | |
| 2 | InternVL3.5-241B-A28B | 51.9% | Aug 2025 | Model card | |
| 3 | STEP3-VL-10B | 51.6% | Jan 2026 | Model card | |
| 4 | GLM-4.5V | 51% | Aug 2025 | Model card | |
| 5 | GLM-4.1V-9B-Thinking | 47.7% | Jul 2025 | Model card |
4 models have held number one since its release in Jun 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Dec 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 |
|---|---|---|---|
| 8 Dec 2025 | GLM-4.6V | 52 | OmniSpatial |
| 25 Aug 2025 | InternVL3.5-241B-A28B | 51.9 | OmniSpatial |
| 11 Aug 2025 | GLM-4.5V | 51 | OmniSpatial |
5 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 |
|---|---|---|---|---|
| 14 Jan 2026 | STEP3-VL-10B technical report | 51.6 | OmniSpatial, SeRe (Tables 1 and 3). PaCoRe 52.58 | Capabilities |
| 1 Jan 2026 | GLM-4.6V technical report | 52 | OmniSpatial, GLM-4.6V thinking (Table 2) | Capabilities |
| 25 Aug 2025 | InternVL3.5-241B-A28B technical report | 51.9 | OmniSpatial (Table 2, Table 11) | Capabilities |
| 13 Aug 2025 | GLM-4.5V technical report | 51 | OmniSpatial, GLM-4.5V thinking (Table 2) | Capabilities |
| 1 Jul 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. Kimi K3.1 Pro 84.1%
- 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% - 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% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%