Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Autoformalization on MATHVERSE Plane Geometry
Loading...
76
Compile Rate
Gemini-3-Pro
-3.04
17.48
38
58.52
Jan 6, 2026
Compile Rate
Semantic Correctness
Human Check Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Compile Rate
Semantic Correctness
Human Check Score
Gemini-3-Pro
Modality=Image
2026.01
76
76
72
Qwen3-VL-235B
Modality=Image
2026.01
28
16
12
GPT-5
Modality=Image
2026.01
24
20
12
Gemini-2.5-Pro
Modality=Image
2026.01
24
20
20
GPT-5
Modality=Text
2026.01
8
0
-
Gemini-3-Pro
Modality=Text
2026.01
8
0
-
Gemini-2.5-Pro
Modality=Text
2026.01
8
0
-
Qwen3-VL-235B
Modality=Text
2026.01
4
0
-
Qwen2.5-VL-72B
Modality=Image
2026.01
0
0
0
Qwen2.5-VL-72B
Modality=Text
2026.01
0
0
-
Feedback
Search any
task
Search any
task