Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended scientific discovery on iNatDisco-50K
Loading...
0.6667
Recall
DiscoPER
-0.026667
0.153333
0.333333
0.513333
Jul 1, 2026
Recall
Support Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Recall
Support Rate
DiscoPER
Type=LLM, H=H_open_cod...
2026.07
0.6667
74.2
DiscoPER w/o Reflect
Type=LLM, H=H_open_cod...
2026.07
0.5
66.6
ExperiGen
Type=LLM, H=H_guided_c...
2026.07
0.25
67.8
HeurekaBench
Type=LLM, H=H_guided_c...
2026.07
0.1667
64.7
LLM+NOTEARS
Type=Causal, H=H_edge,...
2026.07
0.0833
-
GPT-4 BFS
Type=Causal, H=H_edge,...
2026.07
0.0833
-
LLM+PC
Type=Causal, H=H_edge,...
2026.07
0
-
Feedback
Search any
task
Search any
task