List your company

Mathematical Reasoning on MMLU algebra

97Pass@1CoD
73.0879.2985.591.71Jun 5, 2026

Evaluation results

MethodLinks
CoDBackbone=QwQ-32B2026.06971,345
DyConBackbone=QwQ-32B2026.06971,266
NothinkingBackbone=QwQ-32B2026.06961,431
DEERBackbone=QwQ-32B2026.06961,395
BaselineBackbone=Qwen3-14B2026.06962,545
DyConBackbone=Qwen3-14B2026.06962,073
CoDBackbone=Qwen3-4B-Thinking-25072026.06953,209
NoWaitBackbone=Qwen3-4B-Thinking-25072026.06952,068
DyConBackbone=Qwen3-4B-Thinking-25072026.06952,122
BaselineBackbone=QwQ-32B2026.06952,133
SEALBackbone=QwQ-32B2026.06951,541
NoWaitBackbone=QwQ-32B2026.06951,302
BaselineBackbone=Qwen3-4B-Thinking-25072026.06943,496
NothinkingBackbone=Qwen3-4B-Thinking-25072026.06942,331
CoDBackbone=Qwen3-14B2026.06941,381
NoWaitBackbone=Qwen3-14B2026.06931,729
DEERBackbone=Qwen3-4B-Thinking-25072026.06921,945
DyConBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06911,488
Dynasor-CoTBackbone=Qwen3-14B2026.06911,733
BaselineBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06902,387
Controlling Thinking SpeedBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06901,719
NoWaitBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06891,347
ThinkpilotBackbone=Qwen3-14B2026.0688538
DEERBackbone=Qwen3-14B2026.06871,380
CoDBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06851,091
NothinkingBackbone=Qwen3-14B2026.0684547
ThinkpilotBackbone=Qwen3-4B-Thinking-25072026.06831,306
SEALBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06801,507
DEERBackbone=DeepSeek-R1-Distill-Qwen-7B2026.06791,493
NothinkingBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0674760
ThinkpilotBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0674705