Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pour on scientific experiment dataset
Loading...
0.645
Success Rate
CAPER
0.33612
0.41631
0.4965
0.57669
Feb 10, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
CAPER
2026.02
0.645
MLM+RL
Backbone=GPT-4o
2026.02
0.626
MP+MLM+RL
Backbone=GPT-4o
2026.02
0.624
LLM+RL
Backbone=GPT-4o
2026.02
0.546
MLM+RL
Backbone=LLaMA3.2, Rea...
2026.02
0.447
LLM+RL
Backbone=Llama-3.1-8B,...
2026.02
0.348
Feedback
Search any
task
Search any
task
