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

Mathematical Reasoning on Geometry3k

79.9Accuracy

GPT-5-Thinking*

Updated 5d ago

Evaluation Results

Method	Links
GPT-5-Thinking* 2025.09		79.9	-
GPT-5-Thinking* 2026.04		79.9	84.3
Gemini-2.5-Pro* 2025.09		77.2	-
Gemini-2.5-Pro* 2026.04		77.2	80.1
V-STAR 2026.04		69.4	-
ThinkLite-VL 2026.04		68.9	-
VL-Cogito 2026.04		68.7	-
VL-Rethinker 2026.04		67.7	-
Vision-R1 2026.04		67	-
OpenVLThinker 2026.04		60.6	-
Qwen2.5VL 2026.04		59.2	-
R1-Onevision 2026.04		57.9	-
MUPO-Thinker-7B 2026.04		52.1	59.1
VAPO-Thinker-7B 2025.09		51.3	-
VLAA-Thinker-7B 2025.09		50.6	-
VLAA-Thinker-7B 2026.04		50.6	55.2
Vision-R1-7B 2025.09		49	-
Vision-R1-7B 2026.04		49	54.1
R1-OneVision-7B 2025.09		46.1	-
R1-OneVision-7B 2026.04		46.1	50.4
MUPO-Thinker-3B 2026.04		45.1	52.9
InternVL2.5-8B* 2025.09		44.8	-
InternVL2.5-8B* 2026.04		44.8	48
VAPO-Thinker-3B 2025.09		44.2	-
Qwen2.5-VL-7B 2025.09		38.5	-
Qwen2.5-VL-7B 2026.04		38.5	54.4