Last-word prediction on LAMBADA fr
20.6Zero-shot AccuracyMGPT-2
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MGPT-2#Params=124M, Patch size=-, zero-shot evaluation=true2026.04 | 20.6 | — | — | |
| MIXAR stage2#Params=477M, Patch size=32×32, zero-shot evaluation=true2026.04 | 10.4 | 58.9 | 63.3 | |
| GPT-2#Params=124M, Patch size=-, zero-shot evaluation=true2026.04 | 7.9 | — | — | |
| MIXAR stage2#Params=116M, Patch size=32×32, zero-shot evaluation=true2026.04 | 7.7 | 62.1 | 66.4 | |
| PIXAR stage2#Params=113M, Patch size=8×8, zero-shot evaluation=true2026.04 | 5.9 | 60.1 | 64.4 | |
| MIXAR stage1#Params=477M, Patch size=32×32, zero-shot evaluation=true2026.04 | 2.7 | 53 | 57 | |
| MIXAR stage1#Params=116M, Patch size=32×32, zero-shot evaluation=true2026.04 | 1.3 | 45.4 | 49 |