Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Ideation on NeurIPS 2025 (Others)
Loading...
6.92
Novelty
Agentic-Ideation
5.9736
6.2193
6.465
6.7107
Jun 30, 2026
Novelty
Significance
Feasibility
Overall Score
Updated 24d ago
Evaluation Results
Method
Method
Links
Novelty
Significance
Feasibility
Overall Score
Agentic-Ideation
Backbone=Qwen3-8B
2026.06
6.92
7.82
6.02
6.69
SciMON
Underlying LLM=GPT-4o
2026.06
6.28
7.02
5.59
6.03
VirSci
Underlying LLM=GPT-4o
2026.06
6.22
6.86
5.38
6.01
SciPIP
Underlying LLM=GPT-4o
2026.06
6.18
6.94
5.63
5.96
ResearchAgent
Underlying LLM=GPT-4o
2026.06
6.05
6.86
5.54
5.86
Qwen-3-8B
Type=Backbone model
2026.06
6.01
6.91
5.24
6.1
Feedback
Search any
task
Search any
task