List your company

Mathematical Reasoning on AIME 25

94.5AccuracyAPRM
51.3462.54573.7584.955Nov 28, 2025Nov 30, 2025Dec 3, 2025Dec 6, 2025Dec 9, 2025Dec 12, 2025Dec 15, 2025

Evaluation results

MethodLinks
APRMBackbone=GPT-OSS-120B2025.1194.5
APRMBackbone=GPT-OSS-20B2025.1193.6
LLM-JBackbone=GPT-OSS-20B2025.1192.8
APRMBackbone=Gemma-3-27B2025.1191.9
LLM-JBackbone=Gemma-3-27B2025.1191.6
Hard Neg.Backbone=GPT-OSS-120B2025.1191.5
ReST-MCTSBackbone=GPT-OSS-20B2025.1191.3
ReST-MCTSBackbone=GPT-OSS-120B2025.1191
ReST-MCTSBackbone=Gemma-3-27B2025.1190.6
LLM-JBackbone=GPT-OSS-120B2025.1190.4
ToTBackbone=GPT-OSS-20B2025.1190.4
ToTBackbone=GPT-OSS-120B2025.1189.2
Hard Neg.Backbone=Gemma-3-27B2025.1189.1
ToTBackbone=Gemma-3-27B2025.1188
ARMBackbone=GPT-OSS-120B2025.1187.9
QwenLong-L1.5-30B-A3B2025.1286.46
CoT-SCBackbone=GPT-OSS-120B2025.1185.5
Qwen3-30B-A3B-Thinking-25072025.1282.81
ARMBackbone=Gemma-3-27B2025.1171.4
CoT-SCBackbone=GPT-OSS-20B2025.1169.9
CoT-SCBackbone=Gemma-3-27B2025.1169.9
APRMBackbone=Gemma-3-12B2025.1165.7
ReST-MCTSBackbone=Gemma-3-12B2025.1162.6
ToTBackbone=Gemma-3-12B2025.1161.4
LLM-JBackbone=Gemma-3-12B2025.1155.4
CoT-SCBackbone=Gemma-3-12B2025.1153