List your company

Mathematical Reasoning on MATH500, AIME24, AIME25, AMC23

91.5MATH500 ScoreDS-Qwen-7B + LaneRoPE(NTK*)
41.78854.69467.680.506May 26, 2026

Evaluation results

MethodLinks
DS-Qwen-7B + LaneRoPE(NTK*)Train.=KTO, N=22026.0591.546.533.384.263.9
DS-Qwen-7B + LaneRoPE(NTK*)Train.=KTO, N=42026.0590.746.333.685.964.1
DS-Qwen-7B + LaneRoPE(NTK*)Train.=KTO, N=12026.0590.544.434.482.763
DS-Qwen-7B + BridgeTrain.=KTO, N=42026.0589.44033.28561.9
DS-Qwen-7B + LaneRoPE(NTK*)Train.=SFT, N=22026.05893629.175.957.5
DS-Qwen-7B + BridgeTrain.=KTO, N=22026.0588.840.529.281.460
DS-Qwen-7B + LaneRoPE(NTK*)Train.=SFT, N=42026.0587.834.128.581.157.9
DS-Qwen-7B + LaneRoPE(NTK*)Train.=SFT, N=12026.0587.332.628.576.756.3
DS-Qwen-1.5B + BridgeTrain.=KTO, N=42026.058728.727.97354.1
DS-Qwen-1.5B + BridgeTrain.=KTO, N=12026.0586.932.126.674.254.9
DS-Qwen-1.5B + BridgeTrain.=KTO, N=22026.0586.433.425.573.954.8
DS-Qwen-7BTrain.=-, N=12026.0586.325.726.170.252.1
DS-Qwen-7B + BridgeTrain.=KTO, N=12026.0585.539.429.482.859.3
DS-Qwen-7B + LaneRoPE(GT)Train.=-, N=22026.058527.127.970.252.5
DS-Qwen-1.5B + LaneRoPE(NTK*)Train.=KTO, N=42026.0584.626.325.668.751.3
DS-Qwen-1.5B + LaneRoPE(NTK*)Train.=KTO, N=12026.0584.528.324.672.352.4
DS-Qwen-7B + LaneRoPE(NTK)Train.=-, N=22026.0584.328.224.165.250.5
DS-Qwen-1.5B + LaneRoPE(NTK*)Train.=KTO, N=22026.0583.926.325.271.351.7
DS-Qwen-1.5BTrain.=-, N=12026.0579.219.419.156.543.5
DS-Qwen-7B + HogWildTrain.=-, N=22026.0570.420.821.15821.8
DS-Qwen-1.5B + HogWildTrain.=-, N=22026.0558.67.56.643.327.2
DS-Qwen-1.5B + LaneRoPE(GT)Train.=-, N=22026.0543.70020.216