Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Ideation on Scientific Ideation (Human Evaluation)
Loading...
6.71
Novelty
Agentic-Ideation
5.7844
6.0247
6.265
6.5053
Jun 30, 2026
Novelty
Significance
Feasibility
Overall Quality
Updated 24d ago
Evaluation Results
Method
Method
Links
Novelty
Significance
Feasibility
Overall Quality
Agentic-Ideation
2026.06
6.71
7.5
6.05
6.45
Scimon
2026.06
6.07
6.68
5.55
5.76
SciPIP
2026.06
6.02
6.49
5.57
5.87
Qwen3-8B
2026.06
5.96
6.57
5.42
5.55
ResearchAgent
2026.06
5.83
6.41
5.41
5.57
Virsci
2026.06
5.82
6.38
5.43
5.62
Feedback
Search any
task
Search any
task