Our new X account is live! Follow @wizwand_team for updates

Multimodal Autoformalization on PHYX Mechanics

71.4Compile Rate

GPT-5

Updated 3d ago

Evaluation Results

Method	Links
GPT-5 2026.01		71.4	71.4	71.4
Gemini-3-Pro 2026.01		42.9	28.6	-
Gemini-3-Pro 2026.01		28.6	28.6	28.6
GPT-5 2026.01		16.7	0	-
Gemini-2.5-Pro 2026.01		0	0	0
Gemini-2.5-Pro 2026.01		0	0	-
Qwen3-VL-235B 2026.01		0	0	0
Qwen3-VL-235B 2026.01		0	0	-
Qwen2.5-VL-72B 2026.01		0	0	0
Qwen2.5-VL-72B 2026.01		0	0	-