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

Mathematical Reasoning on MathVerse V

67.8Accuracy

EASE-7B

Updated 1mo ago

Evaluation Results

Method	Links
EASE-7B 2026.05		67.8
VPPO-RL-7B 2026.05		67.6
VGPO-7B 2026.05		67.6
PAPO_D-7B 2026.05		66.6
PRPO 2026.06		66.3
VPPO 2026.06		65.5
VL-Rethinker-7B 2026.06		65
PAPO-D 2026.06		64.9
VL-Rethinker-7B 2026.05		64.8
R1-ShareVL-7B 2026.06		64.3
PAPO-G 2026.06		64.1
NoisyRollout-7B 2026.06		63.8
MM-Eureka-7B 2026.05		63.6
MM-Eureka-7B 2026.06		62.4
GRPO 2026.06		61.7
PRPO 2026.06		60.7
PVM-8B (SFT + GRPO) 2026.05		59.8
PEARL-8B 2026.05		58.9
Qwen3-VL-8B (SFT + GRPO) 2026.05		58.5
CFPOG 2026.06		58.43
VPPO 2026.06		58.1
Euclid-8B 2026.05		57.9
PAPO-D 2026.06		57.7
Qwen3-VL-8B (LoRA-SFT + GRPO) 2026.05		57.6
PVM-8B (SFT) 2026.05		57.5
OneThinker-8B 2026.05		57.4
Qwen3-VL-8B (SFT) 2026.05		56.9
ICoT 2026.05		56.1
CoMemo 2026.05		55
Qwen3-VL-8B (LoRA-SFT) 2026.05		55
PVM-4B (SFT + GRPO) 2026.05		55
Qwen3-VL-4B (SFT + GRPO) 2026.05		54.6
PVM-4B (SFT) 2026.05		54.4
Qwen3-VL-4B (LoRA-SFT + GRPO) 2026.05		54.2
PAPO-G 2026.06		53.6
DAPO 2026.06		53.1
MemVR 2026.05		52.9
Qwen3-VL-8B-Instruct 2026.05		52.9
Qwen3-VL-4B (SFT) 2026.05		52.7
Qwen3-VL-4B-Instruct 2026.05		52.4
Qwen3-VL-4B (LoRA-SFT) 2026.05		52.4
GRPO 2026.06		52.3
NoisyRollout-7B 2026.05		51.7
DAPO 2026.06		51
PAPOG 2026.06		50.05
GRPO 2026.06		45.41
Qwen2.5-VL-7B 2026.06		34.3
ThinkLite-VL-7B 2026.05		30.9
Qwen2.5-VL-3B 2026.06		30.1