OpenCodePapers
spatial-reasoning-on-vsi-bench
Visual Reasoning
Spatial Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Accuracy
↕
ModelName
ReleaseDate
↕
Grounded 3D-Aware Spatial Vision-Language Modeling
67.6
GR3D-8B
2026-05-28
VoxAnchor: Explicit Voxel-Semantic Grounding for Spatial Understanding in Videos
✓ Link
66.8
VoxAnchor 4B
2026-09-08
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
✓ Link
64.9
RSI-Nav (Ours)
2026-10-11
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Understanding
61.5
FactoSR-8B-RL
2026-09-08
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
✓ Link
60.0
Spatial-Interactor-8B
2026-09-19
Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models
59.5
P3 (Qwen3-VL-8B, 25% retention)
2026-09-08
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
✓ Link
55.93
MJev-Spatial
2026-10-15
3D-Aware VLMs with Implicit and Explicit Geometries
✓ Link
47.6
VLM-IE3D-4B (extra data)
2026-07-23
StreamSpatial: A Benchmark and Framework for Streaming 3D Visual-Spatial Reasoning
✓ Link
47.3
Stream3D-Mem
2026-09-08
Let VLMs Grade Their Own Thoughts: A Self-Quantification Approach to Reasoning-Aware Reward Modeling
38.7
Video-RAISE-7B
2026-06-03
PointThinker: Point-Incentivized Parallel Thinking for Multimodal Large Language Model
37.7
PointThinker-7B (extra data)
2026-06-03
VAST: Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoning
33.5
VideoVAST-7B (extra data)
2026-06-03
×