Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Language Modeling on Tiny Stories
Loading...
2.5
Perplexity (PPL)
Angular (γ=8)
2.2
4.225
6.25
8.275
Oct 5, 2025
Perplexity (PPL)
Updated 4d ago
Evaluation Results
Method
Method
Links
Perplexity (PPL)
Angular (γ=8)
gamma=8, Sequence Leng...
2025.10
2.5
RACE (P=4, L=4)
P=4, L=4, Sequence Len...
2025.10
2.6
FlashAttention2
Sequence Length=1024
2025.10
2.7
RACE (P=3, L=3)
P=3, L=3, Sequence Len...
2025.10
3.2
Linformer-128
Projection Dimension=1...
2025.10
3.7
Sigmoid
Sequence Length=1024
2025.10
3.7
RACE (P=2, L=2)
P=2, L=2, Sequence Len...
2025.10
4.2
Linear
Sequence Length=1024
2025.10
7
Performer-256
Dimension=256, Sequenc...
2025.10
10
Feedback
Search any
task
Search any
task