Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Visual Reasoning on Math-Reasoning I
Loading...
96.62
Accuracy
Benchmark Agent
91.789
94.2045
96.62
99.0355
Jun 4, 2026
Accuracy
UIA Score
FSQ Score
QAC Score
CQC Score
TSD Score
SSC Score
Overall Accuracy
Accuracy (2B Params)
Accuracy (4B Params)
Accuracy (9B Params)
Accuracy (27B Params)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
UIA Score
FSQ Score
QAC Score
CQC Score
TSD Score
SSC Score
Overall Accuracy
Accuracy (2B Params)
Accuracy (4B Params)
Accuracy (9B Params)
Accuracy (27B Params)
Benchmark Agent
evaluation_type=Human...
2026.06
96.62
79.69
94.72
95.44
87.58
68.08
45.13
77.79
-
-
-
-
Qwen3.5
evaluation_type=Consis...
2026.06
-
-
-
-
-
-
-
-
45.26
47.19
48.88
54.49
Feedback
Search any
task
Search any
task