spatial reasoning benchmark
Hypersim
Hypersim evaluates 3D grounding and depth understanding in synthetic indoor scenes.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
Hypersim Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 0.131 points | 100.0% | 4 | C | |
| 02 | AC | 0.13 points | 66.7% | 4 | C | |
| 03 | AC | 0.127 points | 33.3% | 4 | C | |
| 04 | AC | 0.11 points | 0.0% | 4 | C |
Hypersim Score Distribution
A closer view of the leading scores on this benchmark.
Hypersim Highlights
The leading models and scores on this benchmark.
What is Hypersim?
What Hypersim measures and how its scores work.
Hypersim evaluates 3D grounding and depth understanding in synthetic indoor scenes.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- Hypersim
- Modality
- image
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- hypersim|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Hypersim.
Which model scores highest on Hypersim?
Qwen3.5-35B-A3B is currently ranked first with 0.131 points.
What does Hypersim measure?
Hypersim evaluates 3D grounding and depth understanding in synthetic indoor scenes.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.