Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
One-step next-observation prediction on WebShop (test)
Loading...
63
Token F1
Word2World
26.6
36.05
45.5
54.95
May 29, 2026
Token F1
BLEU-4
Updated 2d ago
Evaluation Results
Method
Method
Links
Token F1
BLEU-4
Word2World
Backbone=Qwen3.5-4B, L...
2026.05
63
42
PoE-World
Backbone=Mimo-v2.5, LL...
2026.05
60
47
LLM-Direct
Backbone=DeepSeek-V4-F...
2026.05
58
36
WorldCoder
Backbone=Qwen3-Coder-4...
2026.05
58
45
WorldCoder
Backbone=DeepSeek-V4-F...
2026.05
58
45
PoE-World
Backbone=Qwen3-Coder-4...
2026.05
58
44
LLM-Direct
Backbone=Qwen3-Coder-4...
2026.05
56
34
WorldCoder
Backbone=Mimo-v2.5, LL...
2026.05
53
37
PatchWorld-Simple
Backbone=Qwen3-Coder-4...
2026.05
53
30
LLM-Direct
Backbone=Mimo-v2.5, LL...
2026.05
52
25
PatchWorld-Residual
Backbone=Qwen3-Coder-4...
2026.05
50
26
PatchWorld-Residual
Backbone=Mimo-v2.5, LL...
2026.05
50
26
PatchWorld-Residual
Backbone=DeepSeek-V4-F...
2026.05
50
26
PoE-World
Backbone=DeepSeek-V4-F...
2026.05
47
33
PatchWorld-Simple
Backbone=Mimo-v2.5, LL...
2026.05
28
12
PatchWorld-Simple
Backbone=DeepSeek-V4-F...
2026.05
28
10
Feedback
Search any
task
Search any
task