MuSR
text
+
+
+
+
About
MUSR (Multimodal Understanding of Spatial Reasoning) is a benchmark designed to evaluate multimodal models' spatial reasoning capabilities across visual and textual modalities. It tests models' ability to understand spatial relationships, navigate complex spatial scenarios, and perform geometric reasoning tasks requiring integration of visual perception and spatial cognition.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
76.4%
Average Score
76.4%
High Performers (80%+)
0Top Organizations
#1Moonshot AI
1 model
76.4%
+
+
+
+
Leaderboard
1 models ranked by performance on MuSR
| License | Links | ||||
|---|---|---|---|---|---|
| Jul 11, 2025 | MIT | 76.4% |
