Writing on WildBench (test)
0.644ScoreFull
Evaluation Results
| Method | Links | |
|---|---|---|
| FullModel=Qwen3, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 0.644 | |
| FrequencyModel=Qwen3, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 0.632 | |
| MoNEModel=Qwen3, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 0.627 | |
| EANModel=Qwen3, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 0.623 | |
| SEERModel=Qwen3, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 0.612 | |
| REAPModel=Qwen3, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 0.6 | |
| MANModel=Qwen3, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 0.57 | |
| MSANModel=Qwen3, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 0.559 | |
| FullModel=ERNIE, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 0.479 | |
| FullModel=OLMoE, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 0.444 | |
| MoNEModel=ERNIE, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 0.419 | |
| FullModel=DeepSeek, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 0.418 | |
| REAPModel=ERNIE, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 0.414 | |
| EANModel=ERNIE, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 0.408 | |
| MSANModel=ERNIE, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 0.404 | |
| MANModel=ERNIE, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 0.402 | |
| SEERModel=ERNIE, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 0.381 | |
| FrequencyModel=ERNIE, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 0.352 | |
| EANModel=DeepSeek, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 0.295 | |
| FrequencyModel=DeepSeek, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 0.291 | |
| REAPModel=OLMoE, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 0.263 | |
| MANModel=OLMoE, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 0.26 | |
| MSANModel=OLMoE, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 0.242 | |
| MSANModel=DeepSeek, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 0.238 | |
| MoNEModel=DeepSeek, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 0.2 | |
| EANModel=OLMoE, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 0.184 | |
| MoNEModel=OLMoE, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 0.181 | |
| REAPModel=DeepSeek, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 0.174 | |
| SEERModel=DeepSeek, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 0.155 | |
| MANModel=DeepSeek, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 0.154 | |
| SEERModel=OLMoE, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 0.141 | |
| FrequencyModel=OLMoE, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 0.127 |