Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on MATH (Clean Error & ASR)
Loading...
43.8
Clean Error
No trust
43.528
45.364
47.2
49.036
Jun 3, 2025
Clean Error
ASR (Answer Success Rate)
Updated 3d ago
Evaluation Results
Method
Method
Links
Clean Error
ASR (Answer Success Rate)
No trust
Communication Structur...
2025.06
43.8
-
A-Trust
Communication Structur...
2025.06
44.6
-
No trust
Communication Structur...
2025.06
46.2
-
No trust
Communication Structur...
2025.06
47.6
-
A-Trust
Communication Structur...
2025.06
48.6
-
A-Trust
Communication Structur...
2025.06
50.6
-
No trust
Communication Structur...
2025.06
-
93.6
A-Trust
Communication Structur...
2025.06
-
18.4
No trust
Communication Structur...
2025.06
-
92.4
A-Trust
Communication Structur...
2025.06
-
19.2
No trust
Communication Structur...
2025.06
-
82.6
A-Trust
Communication Structur...
2025.06
-
16.8
Feedback
Search any
task
Search any
task
