List your company

Mathematical Reasoning on MATH500, AMC23, GSM8K (test)

86.6Accuracy on MATH500HCC
27.52842.86458.273.536May 28, 2026

Evaluation results

MethodLinks
HCCBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}R2026.0586.66596.282.6455.9
EditorBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}R2026.0586.467.59683.3443.2
VanillaBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}Q2026.0585.862.595.881.4519.6
VanillaBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}R2026.0585.662.595.881.3510.6
EditorBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}Q2026.0584.47096.283.5499
HeuristicBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}R2026.0584.462.595.780.9498.5
HeuristicBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}Q2026.0582.857.595.878.7526.1
HCCBackbone=Qwen2.5-Math-7B-Instruct, SFT Data Source=SFT on {T}Q2026.0582.662.596.180.4497.9
EditorBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}R2026.0551.222.575.949.81,942.1
HCCBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}R2026.0547.622.577.849.31,934.4
HCCBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}Q2026.0543.217.575.145.22,010.1
EditorBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}Q2026.0541.82075.445.71,906.1
HeuristicBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}R2026.05401570.141.75,172.1
VanillaBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}R2026.0538.41569.941.14,967.1
HeuristicBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}Q2026.05341571.540.23,430.8
VanillaBackbone=LLaMA3.2-3B-Instruct, SFT Data Source=SFT on {T}Q2026.0529.8106936.33,478.8