Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Autoformalization on PHYX Modern
Loading...
71.4
Compile Rate
GPT-5
-2.856
16.422
35.7
54.978
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
GPT-5
Modality=Image
2026.01
71.4
71.4
42.9
Gemini-3-Pro
Modality=Text
2026.01
57.1
42.9
-
GPT-5
Modality=Text
2026.01
37.5
12.5
-
Gemini-3-Pro
Modality=Image
2026.01
14.3
14.3
14.3
Gemini-2.5-Pro
Modality=Image
2026.01
14.3
14.3
0
Gemini-2.5-Pro
Modality=Text
2026.01
0
0
-
Qwen3-VL-235B
Modality=Image
2026.01
0
0
0
Qwen3-VL-235B
Modality=Text
2026.01
0
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