List your company

Mathematical Reasoning on AIME 2025 1 (Accuracy)

25AccuracyTA-OPD+Ent.
0.73687.035913.33519.6341May 26, 2026

Evaluation results

MethodLinks
TA-OPD+Ent.Setting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0525
TIPSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0523.67
EntropySetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0523.33
Pure OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0521.67
TA-OPD+Ent.Setting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0521.67
Pure OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0521.66
TA-OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0521.31
TA-OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0518.34
TIPSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0516.66
Pure OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0515
TA-OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0515
EntropySetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0515
BaseSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0513.33
BaseSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0513.33
TIPSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0511.67
BaseSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0510
TA-OPD+Ent.Setting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.058.34
EntropySetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.058.33
TA-OPD+Ent.Setting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.053.33
BaseSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.051.67
Pure OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.051.67
EntropySetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.051.67
TIPSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.051.67
TA-OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.051.67