Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial Reasoning on ReSQ
Loading...
85.41
GPT-grid Score
GPT-5.1
68.1876
72.6588
77.13
81.6012
Jun 30, 2026
GPT-grid Score
SM-grid Score
Updated 25d ago
Evaluation Results
Method
Method
Links
GPT-grid Score
SM-grid Score
GPT-5.1
Setting=FG (Full-grid)
2026.06
85.41
-
Qwen3-32B
Setting=PG (Pruned-grid)
2026.06
85.25
79.83
GPT-5.1
Setting=PG (Pruned-grid)
2026.06
84.59
-
Qwen3-32B
Setting=FG (Full-grid)
2026.06
83.28
79.5
GPT-5.1
Setting=Text
2026.06
82.6
-
LLaMA3.1-70B
Setting=FG (Full-grid)
2026.06
80.33
78.2
Qwen3-32B
Setting=Text
2026.06
80.3
80.3
LLaMA3.1-70B
Setting=PG (Pruned-grid)
2026.06
80
78.2
GPT-5.1
Setting=Rel. Trip.
2026.06
79.18
-
LLaMA3.1-70B
Setting=Text
2026.06
77.05
77.05
LLaMA3.1-70B
Setting=Rel. Trip.
2026.06
76.23
69.84
Qwen3-32B
Setting=Rel. Trip.
2026.06
68.85
68.85
Feedback
Search any
task
Search any
task