Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mix on scientific experiment dataset
Loading...
52.3
Success Rate
CAPER
22.14
29.97
37.8
45.63
Feb 10, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
CAPER
2026.02
52.3
MP+MLM+RL
Backbone=GPT-4o
2026.02
43.6
MLM+RL
Backbone=GPT-4o
2026.02
43.2
MLM+RL
Backbone=LLaMA3.2, Rea...
2026.02
35.5
LLM+RL
Backbone=GPT-4o
2026.02
23.8
LLM+RL
Backbone=Llama-3.1-8B,...
2026.02
23.3
Feedback
Search any
task
Search any
task