Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Idea Generation on IdeaBench
Loading...
0.559
Semantic Similarity
FlowPIE
0.47892
0.49971
0.5205
0.54129
Mar 31, 2026
Semantic Similarity
Idea Overlap
Novelty Insight Score
Feasibility Insight Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Semantic Similarity
Idea Overlap
Novelty Insight Score
Feasibility Insight Score
FlowPIE
2026.03
0.559
7.76
0.825
0.105
Research Agent
2026.03
0.558
6.66
0.722
0.138
Initial Population
Description=Initial po...
2026.03
0.532
7.64
0.75
0.136
SCIPIP
2026.03
0.526
5.03
0.816
0.133
VirSci
2026.03
0.521
6.24
0.716
0.075
Chain-of-Ideas
2026.03
0.482
7.24
0.926
0.095
Feedback
Search any
task
Search any
task