Mathematical Reasoning on MATH 500 (TPF, TPS, Acc., AUP Score)
5.94TPFDMax-Math
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| DMax-MathZero-shot=true, Batch size=1, Decoding threshold=0.5, Generation length=2048, Hardware=2x H200 GPUs, Framework=dInFer [54], Prompting strategy=chain-of-thought [80]2026.04 | 5.94 | 1,286 | 75.4 | 507 | |
| dParallel SFTZero-shot=true, Batch size=1, Generation length=2048, Hardware=2x H200 GPUs, Framework=dInFer [54], Prompting strategy=chain-of-thought [80]2026.04 | 3.42 | 823 | 75.8 | 310 | |
| Hierarchical DecodingZero-shot=true, Batch size=1, Decoding threshold=0.2, Generation length=2048, Hardware=2x H200 GPUs, Framework=dInFer [54], Prompting strategy=chain-of-thought [80]2026.04 | 3.01 | 669 | 73 | 268 | |
| LLaDA-2.0-miniZero-shot=true, Batch size=1, Decoding threshold=0.95, Generation length=2048, Hardware=2x H200 GPUs, Framework=dInFer [54], Prompting strategy=chain-of-thought [80]2026.04 | 2.58 | 626 | 75.8 | 257 | |
| Uniform Diffusion TrainingZero-shot=true, Batch size=1, Generation length=2048, Hardware=2x H200 GPUs, Framework=dInFer [54], Prompting strategy=chain-of-thought [80]2026.04 | 2.43 | 530 | 33.6 | 0 |