List your company

Mathematical Reasoning on AIME24, AIME25, MATH500, AMC23, Hmmt25, and Olympiad

61.67AIME 2024 ScoreIH-GRPO
9.233222.846636.4650.0734May 18, 2026

Evaluation results

MethodLinks
IH-GRPOBackbone=Qwen3-8B, Tool=D2026.0561.6747.593.594.333.1367.5866.28
SimpleTIRBackbone=Qwen3-8B, Tool=D2026.0558.3344.6992.5291.0231.3564.5763.75
Dr.GRPOBackbone=Qwen3-8B, Tool=D2026.0557.541.3592.790.5531.9866.563.43
Dr.GRPOBackbone=Qwen3-8B, Tool=C2026.0556.3541.1592.589.1431.0465.0762.54
DAPOBackbone=Qwen3-8B, Tool=D2026.0556.1543.2392.3591.5632.8164.563.43
EH-GRPOBackbone=Qwen3-8B, Tool=D2026.0555.4243.0293.489.1427.8164.162.15
IH-GRPOBackbone=Qwen3-4B, Tool=D2026.0555.3145.8391.459035.164.8863.76
SimpleTIRBackbone=Qwen3-8B, Tool=C2026.0552.9240.3190.2589.5333.5465.2861.97
SimpleTIRBackbone=Qwen3-4B, Tool=D2026.0551.9841.2591.3389.1432.2963.661.6
Dr.GRPOBackbone=Qwen3-4B, Tool=D2026.0551.6743.6588.786.0235.7363.1761.49
DAPOBackbone=Qwen3-8B, Tool=C2026.0551.5638.7588.5288.6731.4664.0760.51
DAPOBackbone=Qwen3-4B, Tool=D2026.0550.140.8391.189.330.6363.1560.85
Dr.GRPOBackbone=Qwen3-4B, Tool=C2026.0549.6942.7190.387.1130.4263.960.69
DAPOBackbone=Qwen3-4B, Tool=C2026.0549.3842.691.1588.8331.8764.5761.4
SimpleTIRBackbone=Qwen3-4B, Tool=C2026.0549.2743.7587.8885.3131.6760.9359.8
EH-GRPOBackbone=Qwen3-4B, Tool=D2026.0541.7735.3190.2583.2826.9861.9256.59
STaRBackbone=Qwen3-8B, Tool=D2026.0540.832580.5567.4228.6552.3249.13
STaRBackbone=Qwen3-8B, Tool=C2026.0538.8527.2979.8567.7326.9853.5549.04
BaseBackbone=Qwen3-8B, Tool=No2026.0534.6923.6584.866.811.0446.4744.58
BaseBackbone=Qwen3-4B, Tool=No2026.0534.1724.6986.3570.712.547.3345.96
STaRBackbone=Qwen3-4B, Tool=D2026.0532.423.6578.4768.1224.6949.7246.18
IH-GRPOBackbone=Qwen3-1.7B, Tool=D2026.0531.1527.583.866.8718.9651.5546.64
Dr.GRPOBackbone=Qwen3-1.7B, Tool=D2026.0529.3726.2582.262.6616.9851.1344.77
SimpleTIRBackbone=Qwen3-1.7B, Tool=D2026.0529.2727.1981.763.6716.5649.1844.6
Dr.GRPOBackbone=Qwen3-1.7B, Tool=C2026.0527.9225.4279.864.3818.3351.5744.57
EH-GRPOBackbone=Qwen3-1.7B, Tool=D2026.0527.8122.682.0264.0617.450.1744.01
SimpleTIRBackbone=Qwen3-1.7B, Tool=C2026.0526.6724.0683.9760.79.6946.341.9
STaRBackbone=Qwen3-4B, Tool=C2026.0526.3522.673.7761.0920.6248.9342.23
DAPOBackbone=Qwen3-1.7B, Tool=C2026.0525.7326.5683.7567.7314.0650.7744.77
DAPOBackbone=Qwen3-1.7B, Tool=D2026.0524.923.5478.7860.0815.8346.5541.61
BaseBackbone=Qwen3-1.7B, Tool=No2026.0522.521.7781.0557.899.5843.339.35
STaRBackbone=Qwen3-1.7B, Tool=D2026.0511.6711.4658.8238.128.4432.5526.84
STaRBackbone=Qwen3-1.7B, Tool=C2026.0511.2512.9264.7243.369.2735.9329.57