Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on 10-domain bilingual corpus (val)
Loading...
8.27
Validation Perplexity
GPT-2
8.2424
8.4287
8.615
8.8013
May 20, 2026
Validation Perplexity
Sparsity
Updated 13d ago
Evaluation Results
Method
Method
Links
Validation Perplexity
Sparsity
GPT-2
Params=201M, Training=...
2026.05
8.27
0
SNN (AuxCE)
Params=194M, Training=...
2026.05
8.88
89
SNN (noAuxCE)
Params=194M, Training=...
2026.05
8.9
89
SNN mean ± std
2026.05
8.905
89
SNN (AuxCE)
Params=194M, Training=...
2026.05
8.91
89
SNN (noAuxCE)
Params=194M, Training=...
2026.05
8.93
89
GPT-2
Params=124M, Training=...
2026.05
8.96
0
Feedback
Search any
task
Search any
task