Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Robotic Planning on LEMMA Stack and Pass tasks (test)
Loading...
75
Success Rate
SG-CoT
37.56
47.28
57
66.72
Mar 18, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
SG-CoT
LLM Backbone=Gemini-2....
2026.03
75
ProgPrompt
LLM Backbone=Gemini-2....
2026.03
59
SG-CoT
LLM Backbone=Qwen3-VL-2B
2026.03
59
InnerMono
LLM Backbone=Gemini-2....
2026.03
48
InnerMono
LLM Backbone=Qwen3-VL-2B
2026.03
45
CLARA
LLM Backbone=Gemini-2....
2026.03
45
ProgPrompt
LLM Backbone=Qwen3-VL-2B
2026.03
44
CLARA
LLM Backbone=Qwen3-VL-2B
2026.03
39
Feedback
Search any
task
Search any
task