Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Science Simulation Reasoning on ScienceWorld
Loading...
56
Accuracy
SKILLGEN
33.12
39.06
45
50.94
May 9, 2026
Accuracy
Absolute Accuracy Change (∆)
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
Absolute Accuracy Change (∆)
SKILLGEN
Model Name=Grok-4-Fast...
2026.05
56
13
SKILLGEN
Model Name=GPT-5.4-Nan...
2026.05
54
25
SKILLGEN
Model Name=Gemma-4-26B...
2026.05
34
16
Feedback
Search any
task
Search any
task
