List your company

Mathematical Reasoning on BRUMO25 (Pass@k)

54.4Pass@1OXAFull
8.01620.05832.144.142Mar 17, 2026

Evaluation results

MethodLinks
OXAFullModel Backbone=Qwen2.5-7B-Math, RLVR Stage=After RLVR (†)2026.0354.490
OXAMLEModel Backbone=Qwen2.5-7B-Math, RLVR Stage=After RLVR (†)2026.0354.390
SFTModel Backbone=Qwen2.5-7B-Math, RLVR Stage=After RLVR (†)2026.0351.683.3
OXAMLEModel Backbone=Qwen2.5-7B-Math, RLVR Stage=Before RLVR2026.0350.990
OXAFullModel Backbone=Qwen2.5-7B-Math, RLVR Stage=Before RLVR2026.0350.990
SFTModel Backbone=Qwen2.5-7B-Math, RLVR Stage=Before RLVR2026.034883.3
SFTLPModel Backbone=Qwen2.5-7B-Math, RLVR Stage=After RLVR (†)2026.0346.180
OXAFullModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=After RLVR (†)2026.0341.876.7
SFTLPModel Backbone=Qwen2.5-7B-Math, RLVR Stage=Before RLVR2026.0341.286.7
OXAMLEModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=After RLVR (†)2026.0339.183.3
OXAMLEModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=Before RLVR2026.0336.183.3
OXAFullModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=Before RLVR2026.0334.783.3
SFTModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=After RLVR (†)2026.0334.676.7
SFTLPModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=Before RLVR2026.0329.873.3
SFTLPModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=After RLVR (†)2026.0329.476.7
SFTModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=Before RLVR2026.032980
BaseModel Backbone=Qwen2.5-1.5B-Math, RLVR Stage=Before RLVR2026.0311.540
BaseModel Backbone=Qwen2.5-7B-Math, RLVR Stage=Before RLVR2026.039.853.3