Share your thoughts, 1 month free Claude Pro on usSee more

Geometric Problem Solving on GeoTrust Tier3 (test)

26Count

Gemini-2.5-pro

Updated 23d ago

Evaluation Results

Method	Links
Gemini-2.5-pro 2025.04		26	43.33
OpenAI-o3 2025.04		26	43.33
Intern-S1 2025.04		25	41.67
DeepSeek-R1 2025.04		22	36.67
Qwen2.5-VL-72B 2025.04		15	25
GPT-4o 2025.04		11	18.33
Claude-3.7-sonnet 2025.04		10	16.67
Qwen2-VL-7B 2025.04		2	3.33
LLaVA-1.5-7B 2025.04		0	0