List your company

Mathematical Problem Solving on AIME

1,289.8AIME ScoreMSV 64
-48.16299.195646.55993.905Jan 23, 2026Jan 29, 2026Feb 5, 2026Feb 11, 2026Feb 18, 2026Feb 24, 2026Mar 3, 2026

Evaluation results

MethodLinks
MSV 64Budget (N)=64, Sequence Scale=642026.031,289.8
Probe + WV 64Budget (N)=64, Weighted Voting=true2026.031,167.81
ProbeBudget (N)=642026.031,149.4
MSV 16Budget (N)=16, Sequence Scale=162026.031,078.29
MSV 1 + WV 64Budget (N)=64, Sequence Scale=1, Weighted Voting=true2026.031,045.05
ProbeBudget (N)=162026.031,024.18
MSV 1Budget (N)=64, Sequence Scale=12026.031,005.34
Probe + WV 16Budget (N)=16, Weighted Voting=true2026.031,000.25
MSV 1 + WV 16Budget (N)=16, Sequence Scale=1, Weighted Voting=true2026.03959.76
MSV 1Budget (N)=16, Sequence Scale=12026.03954.76
MSV 4Budget (N)=4, Sequence Scale=42026.03850.44
ProbeBudget (N)=42026.03823.84
Probe + WV 4Budget (N)=4, Weighted Voting=true2026.03808.66
MSV 1Budget (N)=4, Sequence Scale=12026.03793.35
MSV 1 + WV 4Budget (N)=4, Sequence Scale=1, Weighted Voting=true2026.03789.28
ProbeBudget (N)=12026.03563.44
MSV 1Budget (N)=1, Sequence Scale=12026.03551.56
DeepSeek-R1Model Category=Closed-source Models2026.0186.7
ReMemFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.0261.67
UMEM-Llama-3.2-1BFrozen Executor=Qwen3-8B-Thinking, Parameters=1B2026.0260
UMEM-Qwen3-4BFrozen Executor=Gemini-2.5-Flash, Parameters=4B2026.0260
UMEM-Qwen3-4BFrozen Executor=Qwen3-8B-Thinking, Parameters=4B2026.0258.33
UMEM-Llama-3.2-1BFrozen Executor=Gemini-2.5-Flash, Parameters=1B2026.0258.33
o1-miniModel Category=Closed-source Models2026.0156.7
LoGos(32B)Model Category=Open-source Models (32B), Parameter Count=32B2026.0156.7
Self-RAGFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.0256.67
ReMemFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.0256.67
Qwen3-4B-InstructFrozen Executor=Gemini-2.5-Flash, Parameters=4B2026.0256.67
Qwen3-4B-InstructFrozen Executor=Qwen3-8B-Thinking, Parameters=4B2026.0255
No MemoryFrozen Executor=Gemini-2.5-Flash, Parameters=-2026.0253.33
MempFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.0253.33
No MemoryFrozen Executor=Qwen3-8B-Thinking, Parameters=-2026.0251.67
Llama-3.2-1B-InstructFrozen Executor=Qwen3-8B-Thinking, Parameters=1B2026.0251.67
UMEM-Qwen3-4BFrozen Executor=GPT-5.1, Parameters=4B2026.0251.67
Llama-3.2-1B-InstructFrozen Executor=Gemini-2.5-Flash, Parameters=1B2026.0251.67
Self-RAGFrozen Executor=GPT-5.1, Parameters=API2026.0250
DeepSeek-R1-Distill-Qwen-32BModel Category=Open-source Models (32B), Parameter Count=32B, Model Variant=Distill2026.0146.7
MempFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.0246.67
Qwen3-4B-InstructFrozen Executor=GPT-5.1, Parameters=4B2026.0246.67
MempFrozen Executor=GPT-5.1, Parameters=API2026.0245
UMEM-Llama-3.2-1BFrozen Executor=GPT-5.1, Parameters=1B2026.0245
Llama-3.2-1B-InstructFrozen Executor=GPT-5.1, Parameters=1B2026.0243.33
No MemoryFrozen Executor=GPT-5.1, Parameters=-2026.0240
LoGos(7B)Model Category=Open-source Models (7B), Parameter Count=7B2026.0140
DeepSeek-R1-Distill-Qwen-7BModel Category=Open-source Models (7B), Parameter Count=7B, Model Variant=Distill2026.0133.3
Self-RAGFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.0230
ReMemFrozen Executor=GPT-5.1, Parameters=API2026.0230
Claude3.7-SonnetModel Category=Closed-source Models2026.0130
Qwen2.5-32B-InstructModel Category=Open-source Models (32B), Parameter Count=32B, Model Variant=Instruct2026.0120
Qwen2.5-7B-BaseModel Category=Open-source Models (7B), Parameter Count=7B, Model Variant=Base2026.0113.3
Qwen2.5-32B-BaseModel Category=Open-source Models (32B), Parameter Count=32B, Model Variant=Base2026.0110
Qwen2.5-7B-InstructModel Category=Open-source Models (7B), Parameter Count=7B, Model Variant=Instruct2026.013.3