Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial relationship understanding on MultihopSpatial
Loading...
37.68
Accuracy
Thinking with Grounding Box
3.4744
12.3547
21.235
30.1153
Jun 15, 2026
Accuracy
PASS@4
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
PASS@4
Thinking with Grounding Box
Model scale=4B, Ground...
2026.06
37.68
66.4
Thinking with Grounding Point
Model scale=4B, Ground...
2026.06
37.03
65.4
Thinking with Grounding Point
Model scale=4B, Ground...
2026.06
37.01
65.02
Thinking with Grounding Box
Model scale=4B, Ground...
2026.06
34.89
63.82
Gemma3-27B-IT
Model scale=27B
2026.06
30.94
45.82
Gemma3-12B-IT
Model scale=12B
2026.06
30.08
43.58
Gemma3-4B-IT
Model scale=4B
2026.06
22.7
36.87
Non-grounded Thinking
Model scale=4B, Ground...
2026.06
4.79
11.67
Feedback
Search any
task
Search any
task