Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Continuous Control on MountainCar Drift I - Dynamics Shift
Loading...
100
Success Rate
No Memory (Plain)
-4
23
50
77
Jan 27, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
No Memory (Plain)
Backbone=Qwen3-30B
2026.01
100
Vanilla
Backbone=Qwen3-30B
2026.01
100
Vanilla + GLOVE
Backbone=Qwen3-30B
2026.01
100
MemoryBank
Backbone=Qwen3-30B
2026.01
100
MemoryBank + GLOVE
Backbone=Qwen3-30B
2026.01
100
Voyager
Backbone=Qwen3-30B
2026.01
100
Voyager + GLOVE
Backbone=Qwen3-30B
2026.01
100
Generative Agent
Backbone=Qwen3-30B
2026.01
100
Generative Agent + GLOVE
Backbone=Qwen3-30B
2026.01
100
No Memory (Plain)
LLM Backbone=Llama3.3-70B
2026.01
0
Vanilla
LLM Backbone=Llama3.3-70B
2026.01
0
Vanilla + GLOVE
LLM Backbone=Llama3.3-70B
2026.01
0
MemoryBank
LLM Backbone=Llama3.3-70B
2026.01
0
MemoryBank + GLOVE
LLM Backbone=Llama3.3-70B
2026.01
0
Voyager
LLM Backbone=Llama3.3-70B
2026.01
0
Voyager + GLOVE
LLM Backbone=Llama3.3-70B
2026.01
0
Generative Agent
LLM Backbone=Llama3.3-70B
2026.01
0
Generative Agent + GLOVE
LLM Backbone=Llama3.3-70B
2026.01
0
Feedback
Search any
task
Search any
task