Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Science on ChemBench
Loading...
83.3
Score
AgentSPEX
77.58
79.065
80.55
82.035
Apr 14, 2026
Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Score
AgentSPEX
Model=GPT-5*, Domain=S...
2026.04
83.3
CoT
Model=GPT-5*, Domain=S...
2026.04
78.9
ReAct
Model=GPT-5*, Domain=S...
2026.04
77.8
Feedback
Search any
task
Search any
task