List your company

Mathematical Reasoning on BRUMO 2025 (Accuracy)

93.3AccuracyMajority
31.62847.63963.6579.661Oct 8, 2025Nov 15, 2025Dec 23, 2025Jan 30, 2026Mar 9, 2026Apr 16, 2026May 24, 2026

Evaluation results

MethodLinks
MajorityModel=DeepSeek-R1-8B2026.0593.3
DC-MeanModel=DeepSeek-R1-8B2026.0593.3
DC-TailModel=DeepSeek-R1-8B2026.0593.3
D-CDG (α = 1)Model=DeepSeek-R1-8B2026.0593.3
D-CDG (β = 0)Model=DeepSeek-R1-8B2026.0593.3
CDG (ours)Model=DeepSeek-R1-8B2026.0593.3
CDG (ours)Model=QwQ-32B2026.0590
DC-TailModel=QwQ-32B2026.0586.7
D-CDG (α = 1)Model=QwQ-32B2026.0586.7
DC-MeanModel=gpt-oss-20B2026.0583.3
DC-TailModel=gpt-oss-20B2026.0583.3
D-CDG (α = 1)Model=gpt-oss-20B2026.0583.3
D-CDG (β = 0)Model=gpt-oss-20B2026.0583.3
CDG (ours)Model=gpt-oss-20B2026.0583.3
MajorityModel=gpt-oss-20B2026.0580
MajorityModel=QwQ-32B2026.0580
DC-MeanModel=QwQ-32B2026.0580
D-CDG (β = 0)Model=QwQ-32B2026.0580
Pass@1Model=DeepSeek-R1-8B2026.0579.7
Pass@1Model=QwQ-32B2026.0576.8
Self-Cert.Backbone Model=Qwen3-8B2025.1071
Loc. uniBackbone Model=Qwen3-8B2025.1070
Mean Acc.Backbone Model=Qwen3-8B2025.1068
Glob. uniBackbone Model=Qwen3-8B2025.1068
Pass@1Model=gpt-oss-20B2026.0564.8
Glob. non-uniBackbone Model=DS-R1-Distill-Qwen-7B2025.1064
Low Ent.Backbone Model=Qwen3-8B2025.1064
High Conf.Backbone Model=Qwen3-8B2025.1063
Loc. non-uniBackbone Model=Qwen3-8B2025.1063
Glob. non-uniBackbone Model=Qwen3-8B2025.1061
Low Ent.Backbone Model=DS-R1-Distill-Qwen-7B2025.1056
Loc. uniBackbone Model=DS-R1-Distill-Qwen-7B2025.1056
Mean Acc.Backbone Model=DS-R1-Distill-Qwen-7B2025.1054
Self-Cert.Backbone Model=DS-R1-Distill-Qwen-7B2025.1052
High Conf.Backbone Model=DS-R1-Distill-Qwen-7B2025.1052
DC-TailModel=Gemma-3-27B2026.0546.7
D-CDG (α = 1)Model=Gemma-3-27B2026.0546.7
CDG (ours)Model=Gemma-3-27B2026.0546.7
Glob. uniBackbone Model=DS-R1-Distill-Qwen-7B2025.1044
Loc. uniBackbone Model=DS-R1-Distill-Llama-8B2025.1044
D-CDG (β = 0)Model=Gemma-3-27B2026.0543.3
Mean Acc.Backbone Model=DS-R1-Distill-Llama-8B2025.1040
Glob. uniBackbone Model=DS-R1-Distill-Llama-8B2025.1040
MajorityModel=Gemma-3-27B2026.0540
DC-MeanModel=Gemma-3-27B2026.0540
Loc. non-uniBackbone Model=DS-R1-Distill-Qwen-7B2025.1039
Low Ent.Backbone Model=DS-R1-Distill-Llama-8B2025.1037
High Conf.Backbone Model=DS-R1-Distill-Llama-8B2025.1036
Loc. non-uniBackbone Model=DS-R1-Distill-Llama-8B2025.1036
Glob. non-uniBackbone Model=DS-R1-Distill-Llama-8B2025.1036
Pass@1Model=Gemma-3-27B2026.0535.9
Self-Cert.Backbone Model=DS-R1-Distill-Llama-8B2025.1034