List your company

Mathematical Reasoning on Math-MC (test)

58.04AccuracyCORAL
23.179232.229641.2850.3304Feb 5, 2026

Evaluation results

MethodLinks
CORALBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0258.043.223.0663.3121.89
FewshotBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0256.785.123.1964.4922.09
CCPSBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0255.7422.583.7180.5729.32
CORALBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0245.653.22.7865.4223.12
FewshotBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0244.8920.168.6791.5529.38
CCPSBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0244.434.572.45105.1337.51
CORALBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0243.736.463.3766.2123.47
FewshotBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0239.9513.116.0273.6425.71
CCPSBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0239.9340.933.58111.6141.08
SteerConfBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0238.2811.154.3171.6227.89
ITIBackbone=Qwen2.5-7B-Instruct, Transfer Experiments=Probe 12026.0234.8519.2913.55110.4438.76
SteerConfBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0230.2743.911.72101.6737.09
ITIBackbone=Mistral-7B-Instruct-v0.3, Transfer Experiments=Probe 12026.0227.5575.9436.83156.7751.56
SteerConfBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0226.9428.558.1481.7832.46
ITIBackbone=Deepseek-7B-Chat, Transfer Experiments=Probe 12026.0224.5249.3925.57126.145.12