Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Science on SciBench chemistry
Loading...
90.61
Score
AgentSPEX
85.7324
86.9987
88.265
89.5313
Apr 14, 2026
Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Score
AgentSPEX
Model=GPT-5, Domain=Sc...
2026.04
90.61
ReAct
Model=GPT-5, Domain=Sc...
2026.04
87.79
CoT
Model=GPT-5, Domain=Sc...
2026.04
85.92
Feedback
Search any
task
Search any
task