Question Answering on QA (Avg. Rank)
1.73Average RankTRACELOCK
Evaluation Results
| Method | Links | |
|---|---|---|
| TRACELOCKModel=Dream, Gen len=256, Win./Block=128, Avg. step=121.92026.05 | 1.73 | |
| TRACELOCKModel=Dream, Gen len=128, Win./Block=64, Avg. step=69.62026.05 | 2.02 | |
| TRACELOCKModel=Dream, Gen len=256, Win./Block=64, Avg. step=111.42026.05 | 2.2 | |
| TRACELOCKModel=Dream, Gen len=128, Win./Block=32, Avg. step=66.02026.05 | 2.31 | |
| TRACELOCKModel=LLaDA, Gen len=128, Win./Block=32, Avg. step=89.72026.05 | 2.6 | |
| RandomModel=Dream, Gen len=256, Win./Block=128, Avg. step=256.02026.05 | 2.62 | |
| TRACELOCKModel=LLaDA, Gen len=256, Win./Block=64, Avg. step=160.92026.05 | 2.68 | |
| ConfidenceModel=LLaDA, Gen len=256, Win./Block=64, Avg. step=256.02026.05 | 2.74 | |
| TRACELOCKModel=LLaDA, Gen len=256, Win./Block=128, Avg. step=177.12026.05 | 2.76 | |
| Fast-dLLMModel=LLaDA, Gen len=128, Win./Block=64, Avg. step=69.62026.05 | 2.81 | |
| ConfidenceModel=LLaDA, Gen len=256, Win./Block=128, Avg. step=256.02026.05 | 2.81 | |
| ConfidenceModel=LLaDA, Gen len=128, Win./Block=64, Avg. step=128.02026.05 | 2.83 | |
| TRACELOCKModel=LLaDA, Gen len=128, Win./Block=64, Avg. step=95.92026.05 | 2.87 | |
| Fast-dLLMModel=LLaDA, Gen len=256, Win./Block=64, Avg. step=117.32026.05 | 2.87 | |
| Fast-dLLMModel=LLaDA, Gen len=256, Win./Block=128, Avg. step=107.52026.05 | 2.87 | |
| ConfidenceModel=LLaDA, Gen len=128, Win./Block=32, Avg. step=128.02026.05 | 2.89 | |
| RandomModel=LLaDA, Gen len=256, Win./Block=128, Avg. step=256.02026.05 | 2.96 | |
| ConfidenceModel=Dream, Gen len=128, Win./Block=32, Avg. step=128.02026.05 | 2.96 | |
| Fast-dLLMModel=Dream, Gen len=256, Win./Block=64, Avg. step=201.82026.05 | 3.01 | |
| L2PModel=LLaDA, Gen len=128, Win./Block=32, Avg. step=64.62026.05 | 3.02 | |
| ConfidenceModel=Dream, Gen len=128, Win./Block=64, Avg. step=128.02026.05 | 3.04 | |
| Fast-dLLMModel=LLaDA, Gen len=128, Win./Block=32, Avg. step=73.02026.05 | 3.06 | |
| ConfidenceModel=Dream, Gen len=256, Win./Block=64, Avg. step=256.02026.05 | 3.06 | |
| Fast-dLLMModel=Dream, Gen len=128, Win./Block=32, Avg. step=106.22026.05 | 3.09 | |
| RandomModel=Dream, Gen len=256, Win./Block=64, Avg. step=256.02026.05 | 3.09 | |
| L2PModel=LLaDA, Gen len=128, Win./Block=64, Avg. step=51.72026.05 | 3.1 | |
| RandomModel=Dream, Gen len=128, Win./Block=64, Avg. step=128.02026.05 | 3.12 | |
| L2PModel=Dream, Gen len=128, Win./Block=32, Avg. step=109.32026.05 | 3.13 | |
| ConfidenceModel=Dream, Gen len=256, Win./Block=128, Avg. step=256.02026.05 | 3.16 | |
| Fast-dLLMModel=Dream, Gen len=128, Win./Block=64, Avg. step=83.52026.05 | 3.19 | |
| Fast-dLLMModel=Dream, Gen len=256, Win./Block=128, Avg. step=140.62026.05 | 3.19 | |
| L2PModel=LLaDA, Gen len=256, Win./Block=64, Avg. step=90.52026.05 | 3.21 | |
| L2PModel=Dream, Gen len=128, Win./Block=64, Avg. step=89.22026.05 | 3.23 | |
| L2PModel=Dream, Gen len=256, Win./Block=64, Avg. step=205.72026.05 | 3.28 | |
| RandomModel=Dream, Gen len=128, Win./Block=32, Avg. step=128.02026.05 | 3.38 | |
| RandomModel=LLaDA, Gen len=128, Win./Block=64, Avg. step=128.02026.05 | 3.4 | |
| RandomModel=LLaDA, Gen len=128, Win./Block=32, Avg. step=128.02026.05 | 3.42 | |
| RandomModel=LLaDA, Gen len=256, Win./Block=64, Avg. step=256.02026.05 | 3.51 | |
| L2PModel=Dream, Gen len=256, Win./Block=128, Avg. step=133.22026.05 | 3.54 | |
| L2PModel=LLaDA, Gen len=256, Win./Block=128, Avg. step=60.12026.05 | 3.59 |