Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended scientific discovery on 40-task evaluation set Overall 2025
Loading...
4.78
Expert Score (ES)
OpenEvolve
3.6568
3.9484
4.24
4.5316
Jun 10, 2026
Expert Score (ES)
Discovery Value (DV)
Number of Claims
High-Quality (HQ) Count
High-Quality (HQ) Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Expert Score (ES)
Discovery Value (DV)
Number of Claims
High-Quality (HQ) Count
High-Quality (HQ) Rate
OpenEvolve
2026.06
4.78
1.44
351
16
4.6
Raw agent
2026.06
4.22
2.47
381
47
12.3
SAGA
2026.06
3.8
2.66
250
52
20.8
StatefulDiscovery
2026.06
3.76
3.09
261
64
24.5
AutoDiscovery
2026.06
3.7
2.59
387
36
9.3
Feedback
Search any
task
Search any
task