Commonsense Reasoning on Common-sense Reasoning Suite (Zero-shot)
52.92Average Accuracy (8 Tasks)HADES
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HADESNumber of Parameters=1B, Zero-shot=true2026.03 | 52.92 | — | — | — | — | — | — | — | — | |
| DeltaNetNumber of Parameters=1.3B, Zero-shot=true2026.03 | 52.53 | — | — | — | — | — | — | — | — | |
| Mamba2Number of Parameters=1.3B, Zero-shot=true2026.03 | 52.46 | — | — | — | — | — | — | — | — | |
| RetNetNumber of Parameters=1.3B, Zero-shot=true2026.03 | 50.31 | — | — | — | — | — | — | — | — | |
| HADESEvaluation Mode=zero-shot2026.03 | 42.91 | 39.24 | 58.84 | 32.82 | 52.64 | 45.03 | 22.01 | 63.93 | 28.8 | |
| Mamba2Evaluation Mode=zero-shot2026.03 | 41.63 | 36.46 | 53.88 | 32.62 | 50.83 | 45.29 | 24.15 | 63.44 | 26.4 | |
| RetNetEvaluation Mode=zero-shot2026.03 | 41.54 | 35.36 | 55.57 | 31.31 | 51.7 | 44.49 | 23.46 | 62.4 | 28 | |
| DeltaNetEvaluation Mode=zero-shot2026.03 | 41.33 | 35.75 | 54.07 | 31.4 | 49.96 | 44.11 | 22.18 | 63.6 | 29.6 | |
| Linear TransformerEvaluation Mode=zero-shot2026.03 | 39.63 | 24.06 | 61.5 | 28.2 | 51.3 | 42.05 | 21.76 | 60.55 | 27.6 | |
| Mamba1Evaluation Mode=zero-shot2026.03 | 39.47 | 22.43 | 62.17 | 28.71 | 50.67 | 42.09 | 22.35 | 60.72 | 26.6 |