Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Grid-world Navigation on FrozenLake reward reversal Source
Loading...
90
Score
Vanilla
-3.6
20.7
45
69.3
Jan 27, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
Vanilla
Backbone=Qwen3-30B, Ag...
2026.01
90
MemoryBank
Backbone=Qwen3-30B, Ag...
2026.01
90
Generative Agent
Backbone=Qwen3-30B, Ag...
2026.01
90
Vanilla + GLOVE
Backbone=Qwen3-30B, Ag...
2026.01
85
MemoryBank + GLOVE
Backbone=Qwen3-30B, Ag...
2026.01
85
Voyager
Backbone=Qwen3-30B, Ag...
2026.01
85
Voyager + GLOVE
Backbone=Qwen3-30B, Ag...
2026.01
85
Generative Agent + GLOVE
Backbone=Qwen3-30B, Ag...
2026.01
85
Vanilla
Backbone=Llama3.3-70B,...
2026.01
42.5
Vanilla + GLOVE
Backbone=Llama3.3-70B,...
2026.01
42.5
Generative Agent + GLOVE
Backbone=Llama3.3-70B,...
2026.01
42.5
Voyager
Backbone=Llama3.3-70B,...
2026.01
40
Voyager + GLOVE
Backbone=Llama3.3-70B,...
2026.01
40
Generative Agent
Backbone=Llama3.3-70B,...
2026.01
40
MemoryBank
Backbone=Llama3.3-70B,...
2026.01
35
MemoryBank + GLOVE
Backbone=Llama3.3-70B,...
2026.01
35
No Memory (Plain)
Backbone=Llama3.3-70B,...
2026.01
0
No Memory (Plain)
Backbone=Qwen3-30B, Ag...
2026.01
0
Feedback
Search any
task
Search any
task