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

Mathematical Reasoning on LogicVista

73.8Accuracy

Gemini-2.5-Pro*

Updated 26d ago

Evaluation Results

Method	Links
Gemini-2.5-Pro* 2025.09		73.8	-	-
GPT-5-Thinking* 2025.09		70	-	-
GPT-4o 2025.11		64.4	-	-
MM-Eureka-Qwen-32B 2025.11		54.6	-	-
MM-Eureka-Qwen-32B 2025.11		52.8	-	-
Gemini-2.0-Flash 2025.11		52.3	-	-
MM-Eureka-Qwen-7B 2025.11		51	-	-
VAPO-Thinker-7B 2025.09		50.9	-	-
Vision-R1-7B 2025.09		49.7	-	-
VL-Rethinker-7B 2025.11		49.7	-	-
Claude-3.5 Sonnet 2025.11		49.3	-	-
MM-Eureka-Qwen-7B 2025.11		49.2	-	-
VLAA-Thinker-7B 2025.09		48.5	-	-
VL-Rethinker-7B 2025.11		46.1	-	-
R1-OneVision-7B 2025.09		45.6	-	-
MMR1-Math-v0-7B 2025.11		44.5	-	-
InternVL3-8B 2025.11		43.6	-	-
MMR1-Math-v0-7B 2025.11		43.6	-	-
Kimi-VL-16B 2025.11		42.7	-	-
QvQ-72B-Preview 2025.11		42.7	-	-
Qwen2.5-VL-7B 2025.09		42.6	-	-
GPT-4o-mini 2025.11		41.4	-	-
VAPO-Thinker-3B 2025.09		39.7	-	-
InternVL2.5-8B* 2025.09		38.3	-	-
Qwen2.5-VL-7B 2025.11		35.6	-	-
LLaVA-OV-7B 2025.11		32	-	-
Qwen2.5-VL-3B 2025.11		26.6	-	-
GPT-5-Thinking* 2026.04		-	70	81.5
Gemini-2.5-Pro* 2026.04		-	73.8	76.4
Qwen2.5-VL-7B 2026.04		-	42.6	59.3
InternVL2.5-8B* 2026.04		-	38.3	44.7
R1-OneVision-7B 2026.04		-	45.6	52.5
VLAA-Thinker-7B 2026.04		-	48.5	54.5
Vision-R1-7B 2026.04		-	49.7	53.8
MUPO-Thinker-3B 2026.04		-	42.8	50.3
MUPO-Thinker-7B 2026.04		-	50.6	61.5