List your company

Mathematical Reasoning on MATH-500 1 (test)

93.2AccuracyMajority Voting
9.615231.315153.01574.7149May 26, 2026May 27, 2026

Evaluation results

MethodLinks
Majority VotingModel=Qwen3-8B, k=322026.0593.2
Marginal SharpeningModel=Qwen3-8B, K=4, S=82026.0592.8
Marginal SharpeningModel=Qwen3-8B, K=32, S=12026.0592.4
Majority VotingModel=Qwen3-1.7B, k=322026.0592
Marginal SharpeningModel=Qwen3-1.7B, K=32, S=12026.0590.8
Marginal SharpeningModel=Qwen3-1.7B, K=4, S=82026.0590.4
TA-OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0587.4
TA-OPD+Ent.Setting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0587
TIPSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0586.2
EntropySetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0585.5
Majority VotingModel=Qwen3-4B, k=322026.0584.8
Pure OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0584.7
Temperature SamplingModel=Qwen3-8B2026.0584.5
Marginal SharpeningModel=Qwen3-4B, K=4, S=82026.0584.2
EntropySetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0584
Marginal SharpeningModel=Qwen3-4B, K=32, S=12026.0584
BaseSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0583.6
BaseSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0583.6
Pure OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0583.5
TA-OPD+Ent.Setting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0583.2
TA-OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0582.5
TIPSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0582.4
Temperature SamplingModel=Qwen3-1.7B2026.0580.6
Power SamplingModel=Qwen3-1.7B2026.0576.2
TIPSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0575.6
Pure OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0575
TA-OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0574.7
TA-OPD+Ent.Setting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0574.7
EntropySetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0574.4
BaseSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0572.6
Temperature SamplingModel=Qwen3-4B2026.0570.9
Power SamplingModel=Qwen3-4B2026.0569.4
BaseSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0556.31
TA-OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0555.31
Pure OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0552.5
TA-OPD+Ent.Setting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0552.2
TIPSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0551.4
EntropySetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0512.83