Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Physical Reasoning on UGPhysics
Loading...
21.7
Pass@1 Accuracy
AERO
12.444
14.847
17.25
19.653
Feb 3, 2026
Pass@1 Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
AERO
Backbone Model=Qwen3-8...
2026.02
21.7
AERO
Backbone Model=Qwen3-8...
2026.02
19.7
AERO
Backbone Model=Qwen3-4...
2026.02
19.4
AERO
Backbone Model=Qwen3-4...
2026.02
18.5
AERO
Backbone Model=Qwen3-8...
2026.02
16.4
AERO
Backbone Model=Qwen3-4...
2026.02
16.2
AERO
Backbone Model=Qwen3-4...
2026.02
15.3
AERO
Backbone Model=Qwen3-8...
2026.02
14.8
AERO
Backbone Model=Qwen3-4...
2026.02
13.2
Qwen3-8B-Base
Backbone Model=Qwen3-8...
2026.02
13.2
AERO
Backbone Model=Qwen3-8...
2026.02
13.2
Qwen3-4B-Base
Backbone Model=Qwen3-4...
2026.02
12.8
Feedback
Search any
task
Search any
task