Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stir on scientific experiment dataset
Loading...
74.4
Success Rate
CAPER
28.432
40.366
52.3
64.234
Feb 10, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
CAPER
2026.02
74.4
MP+MLM+RL
Backbone=GPT-4o
2026.02
70.8
MLM+RL
Backbone=GPT-4o
2026.02
70.5
MLM+RL
Backbone=LLaMA3.2, Rea...
2026.02
39.6
LLM+RL
Backbone=GPT-4o
2026.02
34.8
LLM+RL
Backbone=Llama-3.1-8B,...
2026.02
30.2
Feedback
Search any
task
Search any
task