List your company

Geometric Problem Solving on GeoTrust (test)

45.83AccuracyOpenAI-o3
-0.096411.826823.7535.6732Apr 22, 2025

Evaluation results

MethodLinks
OpenAI-o3#Params=-2025.0445.83110
OpenAI-o3Release Date=Apr, 20252025.0445.83—
Intern-S1#Params=235B+6B2025.0443.33104
Gemini-2.5-pro#Params=-2025.0443.33104
Intern-S1Release Date=Jul, 20252025.0443.33—
Gemini-2.5-proRelease Date=Jun, 20252025.0443.33—
DeepSeek-R1#Params=671B, input_format=only natural language questions, no images2025.0437.0889
Qwen2.5-VL-72B#Params=72B2025.0428.3368
Qwen2.5-VL-72BRelease Date=Jan, 20252025.0428.33—
Claude-3.7-sonnet#Params=-2025.0427.566
Claude-3.7-sonnetRelease Date=Feb, 20252025.0427.5—
GPT-4o#Params=-2025.0425.8362
GPT-4oRelease Date=May, 20242025.0425.83—
Qwen2-VL-7B#Params=7B2025.044.5811
LLaVA-1.5-7B#Params=7B2025.041.674