Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Scientific Discovery on BLADE open-ended discovery (evaluation set)
Loading...
4.8
Expert Score
OpenEvolve
3.4272
3.7836
4.14
4.4964
Jun 10, 2026
Expert Score
Discovery Value
Claims Generated
High-Quality Count
High-Quality Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Expert Score
Discovery Value
Claims Generated
High-Quality Count
High-Quality Rate
OpenEvolve
2026.06
4.8
1.44
91
3
3.3
AutoDiscovery
2026.06
4.42
2.63
130
11
8.5
Raw agent
2026.06
4.11
2.33
115
11
9.6
StatefulDiscovery
2026.06
3.95
2.86
86
22
25.6
SAGA
2026.06
3.48
2.37
96
11
11.5
Feedback
Search any
task
Search any
task