List your company

Mathematical Reasoning on MATH500 (Accuracy and Avg Gain)

82.63AccuracyMIND
44.534854.424964.31574.2051Jan 7, 2026

Evaluation results

MethodLinks
MINDBackbone=Qwen2.5-7B, Fusion=with2026.0182.63—
MCCBackbone=Qwen2.5-7B, Fusion=none2026.0182.22.71
MINDBackbone=Qwen2.5-7B, Fusion=without2026.0180.62.31
EDITBackbone=Qwen2.5-7B, Fusion=none2026.0179.51.53
MoDEBackbone=Qwen2.5-7B, Fusion=none2026.0177.672.23
SbSBackbone=Qwen2.5-7B, Fusion=none2026.0177.42.23
BaseBackbone=Qwen2.5-7B-Instruct, Fusion=none2026.0177.23.99
MINDBackbone=Qwen2.5-1.5B, Fusion=with2026.0154.09—
MINDBackbone=Llama3.1-8B, Fusion=with2026.0153.73—
MCCBackbone=Qwen2.5-1.5B, Fusion=none2026.0153.63.16
MCCBackbone=Llama3.1-8B, Fusion=none2026.01532.63
EDITBackbone=Llama3.1-8B, Fusion=none2026.0152.80.62
SbSBackbone=Llama3.1-8B, Fusion=none2026.0152.60.67
MoDEBackbone=Qwen2.5-1.5B, Fusion=none2026.0152.63.72
MINDBackbone=Qwen2.5-1.5B, Fusion=without2026.01524.41
MINDBackbone=Llama3.1-8B, Fusion=without2026.0151.63.78
EDITBackbone=Qwen2.5-1.5B, Fusion=none2026.0151.22.71
MoDEBackbone=Llama3.1-8B, Fusion=none2026.0150.414.28
BaseBackbone=Qwen2.5-1.5B-Instruct, Fusion=none2026.0150.43.63
SbSBackbone=Qwen2.5-1.5B, Fusion=none2026.0149.83.73
BaseBackbone=Llama3.1-8B-Instruct, Fusion=none2026.01464.11