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

Mathematical Problem Solving on AIME

1,289.8AIME Score

MSV 64

Updated 1mo ago

Evaluation Results

Method	Links
MSV 64 2026.03		1,289.8
Probe + WV 64 2026.03		1,167.81
Probe 2026.03		1,149.4
MSV 16 2026.03		1,078.29
MSV 1 + WV 64 2026.03		1,045.05
Probe 2026.03		1,024.18
MSV 1 2026.03		1,005.34
Probe + WV 16 2026.03		1,000.25
MSV 1 + WV 16 2026.03		959.76
MSV 1 2026.03		954.76
MSV 4 2026.03		850.44
Probe 2026.03		823.84
Probe + WV 4 2026.03		808.66
MSV 1 2026.03		793.35
MSV 1 + WV 4 2026.03		789.28
Probe 2026.03		563.44
MSV 1 2026.03		551.56
DeepSeek-R1 2026.01		86.7
ReMem 2026.02		61.67
UMEM-Llama-3.2-1B 2026.02		60
UMEM-Qwen3-4B 2026.02		60
UMEM-Qwen3-4B 2026.02		58.33
UMEM-Llama-3.2-1B 2026.02		58.33
o1-mini 2026.01		56.7
LoGos(32B) 2026.01		56.7
Self-RAG 2026.02		56.67
ReMem 2026.02		56.67
Qwen3-4B-Instruct 2026.02		56.67
Qwen3-4B-Instruct 2026.02		55
No Memory 2026.02		53.33
Memp 2026.02		53.33
No Memory 2026.02		51.67
Llama-3.2-1B-Instruct 2026.02		51.67
UMEM-Qwen3-4B 2026.02		51.67
Llama-3.2-1B-Instruct 2026.02		51.67
Self-RAG 2026.02		50
DeepSeek-R1-Distill-Qwen-32B 2026.01		46.7
Memp 2026.02		46.67
Qwen3-4B-Instruct 2026.02		46.67
Memp 2026.02		45
UMEM-Llama-3.2-1B 2026.02		45
Llama-3.2-1B-Instruct 2026.02		43.33
No Memory 2026.02		40
LoGos(7B) 2026.01		40
DeepSeek-R1-Distill-Qwen-7B 2026.01		33.3
Self-RAG 2026.02		30
ReMem 2026.02		30
Claude3.7-Sonnet 2026.01		30
Qwen2.5-32B-Instruct 2026.01		20
Qwen2.5-7B-Base 2026.01		13.3
Qwen2.5-32B-Base 2026.01		10
Qwen2.5-7B-Instruct 2026.01		3.3