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

Multimodal Mathematical Reasoning on MathVerse

62.4Average Score

MathFlow-P-7B

Updated 23d ago

Evaluation Results

Method
MathFlow-P-7B 2025.03	62.4	-	-	-	-	-
MathFlow-P-7B 2025.03	60.8	-	-	-	-	-
Gemini 2.5-pro 2025.03	59.9	-	-	-	-	-
MathFlow-P-7B 2025.03	59.5	-	-	-	-	-
MathFlow-P-7B 2025.03	58.9	-	-	-	-	-
GPT-4o 2025.03	57.9	-	-	-	-	-
Claude-sonnet-3.5 2025.03	57.4	-	-	-	-	-
Vision-R1 (7B) 2025.08	57.3	-	-	-	-	-
MathFlow-P-7B 2025.03	56.8	-	-	-	-	-
MathFlow-P-7B 2025.03	56.7	-	-	-	-	-
Vision-SR1 2025.08	54.5	-	-	-	-	-
GPT-4V 2025.03	54.4	-	-	-	-	-
Vision-R1 2025.08	53.2	-	-	-	-	-
GPT-4o-mini 2025.03	52.7	-	-	-	-	-
Percention-R1 (7B) 2025.08	52.1	-	-	-	-	-
Zero-shot Inference 2025.08	49.2	-	-	-	-	-
SophiaVL-R1-7B 2025.05	48.8	45.4	43.9	45.1	58.5	51.3
MathFlow-P-7B 2025.03	48.1	-	-	-	-	-
R1-OneVision-7B 2025.05	46.4	-	40	-	-	-
Vision-SR1 2025.08	45.8	-	-	-	-	-
URSA-8B 2025.05	45.7	46.4	34.6	43.9	55.3	48.3
VL-Rethinker-7B 2026.05	45.68	-	-	-	-	-
Qwen2.5-VL-7B-Instruct + GRPO 2025.05	45.3	43	41	41.1	56	45.6
Visionary-R1 (3B) 2025.08	45	-	-	-	-	-
Qwen2.5-VL-7B + SRPO 2026.05	44.92	-	-	-	-	-
Zero-shot Inference 2025.08	44.3	-	-	-	-	-
Qwen2.5-VL-7B-Instruct 2025.05	44	41.1	41	38.7	55.2	44
MathFlow-P-7B 2025.03	43.3	-	-	-	-	-
InternVL-2.5-78B 2025.03	43.2	-	-	-	-	-
Qwen2.5-VL-7B-Instruct + SFT + GRPO 2025.05	43.1	42.5	37.1	37.3	52.2	46.3
VPPO-7B 2026.05	43.02	-	-	-	-	-
Vision-R1 2025.08	42.8	-	-	-	-	-
Vision-Matters-7B 2026.05	42.79	-	-	-	-	-
Qwen2.5-VL-7B + DAPO 2026.05	41.62	-	-	-	-	-
PAPO-G-7B 2026.05	41.24	-	-	-	-	-
PRCO-7B 2026.05	40.86	-	-	-	-	-
Perception-R1-7B 2026.05	40.35	-	-	-	-	-
Vision-SR1 2025.08	40	-	-	-	-	-
Qwen2.5-VL-3B + SRPO 2026.05	39.72	-	-	-	-	-
Vision-SR1-7B 2026.05	39.46	-	-	-	-	-
Qwen2-VL-72B 2025.03	38.9	-	-	-	-	-
Qwen2.5-VL-7B + GRPO 2026.05	38.71	-	-	-	-	-
PAPO-D-7B 2026.05	38.7	-	-	-	-	-
MathFlow-P-7B 2025.03	38.1	-	-	-	-	-
ThinkLite-VL-7B 2026.05	37.22	-	-	-	-	-
PAPO-D-3B 2026.05	37.18	-	-	-	-	-
Qwen-VL-MaX 2025.03	36.2	-	-	-	-	-
PRCO-3B 2026.05	35.53	-	-	-	-	-
Zero-shot Inference 2025.08	35.5	-	-	-	-	-
Qwen2.5-VL-3B + DAPO 2026.05	35.41	-	-	-	-	-
Vision-R1 2025.08	35.3	-	-	-	-	-
InfiMM-Math 2025.03	34.5	-	-	-	-	-
Vision-SR1-3B 2026.05	34.01	-	-	-	-	-
PAPO-G-3B 2026.05	33.88	-	-	-	-	-
Math-PUMA-Qwen2VL-7B 2025.05	33.6	33.4	26	31.6	42.1	35
Qwen2.5-VL-7B 2026.05	33.37	-	-	-	-	-
Qwen2.5-VL-3B + GRPO 2026.05	33.24	-	-	-	-	-
GPT-4V 2025.05	32.8	-	-	-	-	-
InternVL2.5-8B-VisualPRM 2025.05	30.7	28.9	35.8	27.3	31.7	29.7
Qwen2.5-VL-3B 2026.05	30.32	-	-	-	-	-
MathFlow-P-7B 2025.03	30.2	-	-	-	-	-
LLaVA-OneVision-72B 2025.05	27.2	-	-	-	-	-
Multimath-7B 2025.05	26.9	28.1	15	25.9	34.8	30.8
LLaVA-OneVision-7B 2025.05	26.2	-	-	-	-	-
InternLM-XC2 2025.03	25.9	-	-	-	-	-
Math-LLaVA-13B 2025.05	22.9	24.5	16.1	21.7	27.3	24.9