Mathematical Reasoning on MATH500 (Acc, TPF)
79.2AccuracyMBD-LLaDA2-Mini
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MBD-LLaDA2-MiniBackbone=LLaDA2-Mini, bufsz=2, blksz=322026.06 | 79.2 | 6.02 | |
| SingleBD (Native)Backbone=LLaDA2-Mini-DMax, bufsz=2, blksz=322026.06 | 76.8 | 6.13 | |
| MBD-LLaDA2-Mini-DMaxBackbone=LLaDA2-Mini-DMax, bufsz=2, blksz=322026.06 | 75 | 9.31 | |
| SingleBD (Native)Backbone=LLaDA2-Mini, bufsz=2, blksz=322026.06 | 74.2 | 2.83 | |
| MultiBD (training-free)Backbone=LLaDA2-Mini-DMax, bufsz=2, blksz=322026.06 | 73.8 | 9.08 | |
| MultiBD (training-free)Backbone=LLaDA2-Mini, bufsz=2, blksz=322026.06 | 73.6 | 3.53 | |
| SingleBD (Native)Backbone=SDAR-8B-Chat-b4, bufsz=4, blksz=42026.06 | 72.8 | 1.46 | |
| MBD-SDAR-8B-Chat-b4Backbone=SDAR-8B-Chat-b4, bufsz=4, blksz=42026.06 | 72.4 | 2.52 | |
| MultiBD (training-free)Backbone=SDAR-8B-Chat-b4, bufsz=4, blksz=42026.06 | 70.6 | 2.68 | |
| MBD-SDAR-8B-Chat-b32Backbone=SDAR-8B-Chat-b32, bufsz=4, blksz=322026.06 | 68 | 5.08 | |
| SingleBD (Native)Backbone=SDAR-8B-Chat-b32, bufsz=4, blksz=322026.06 | 65.6 | 3.81 | |
| MultiBD (training-free)Backbone=SDAR-8B-Chat-b32, bufsz=4, blksz=322026.06 | 60.6 | 5.06 |