Multiple Choice on Multiple Choice MC Avg (test)
73.7Average AccuracyFull
Evaluation Results
| Method | Links | |
|---|---|---|
| FullModel=Qwen3, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 73.7 | |
| EANModel=Qwen3, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 73.5 | |
| SEERModel=Qwen3, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 73.4 | |
| MoNEModel=Qwen3, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 73.3 | |
| FrequencyModel=Qwen3, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 73.2 | |
| MANModel=Qwen3, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 72.7 | |
| MSANModel=Qwen3, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 72.7 | |
| FullModel=ERNIE, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 72.1 | |
| REAPModel=Qwen3, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 72.1 | |
| MANModel=ERNIE, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 70.5 | |
| MSANModel=ERNIE, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 70.4 | |
| REAPModel=ERNIE, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 70 | |
| EANModel=ERNIE, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 68.2 | |
| FullModel=DeepSeek, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 67.8 | |
| MoNEModel=ERNIE, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 67.8 | |
| SEERModel=ERNIE, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 65.8 | |
| FrequencyModel=ERNIE, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 65.5 | |
| FullModel=OLMoE, Pruning Ratio=0%, Criterion=Full, Calibration=C42026.06 | 65.3 | |
| MANModel=DeepSeek, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 63.6 | |
| MSANModel=DeepSeek, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 63 | |
| MoNEModel=DeepSeek, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 62.9 | |
| EANModel=DeepSeek, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 62.1 | |
| REAPModel=DeepSeek, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 62 | |
| FrequencyModel=DeepSeek, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 60.2 | |
| SEERModel=DeepSeek, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 60.2 | |
| REAPModel=OLMoE, Pruning Ratio=25%, Criterion=REAP, (b, α, β)=(1, 1, 1), Calibration=C42026.06 | 60.1 | |
| MANModel=OLMoE, Pruning Ratio=25%, Criterion=MAN, (b, α, β)=(1, 0, 1), Calibration=C42026.06 | 59.4 | |
| MSANModel=OLMoE, Pruning Ratio=25%, Criterion=MSAN, (b, α, β)=(1, 0, 2), Calibration=C42026.06 | 58.9 | |
| MoNEModel=OLMoE, Pruning Ratio=25%, Criterion=MoNE, Calibration=C42026.06 | 58.3 | |
| EANModel=OLMoE, Pruning Ratio=25%, Criterion=EAN, (b, α, β)=(0, 0, 1), Calibration=C42026.06 | 58.2 | |
| SEERModel=OLMoE, Pruning Ratio=25%, Criterion=SEER, (b, α, β)=(0, 1, 0), Calibration=C42026.06 | 56.4 | |
| FrequencyModel=OLMoE, Pruning Ratio=25%, Criterion=Frequency, (b, α, β)=(0, 0, 0), Calibration=C42026.06 | 56 |