Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Best Research Idea Selection on D_group
Loading...
65.12
Best Score
InnoEval
19.1624
31.0937
43.025
54.9563
Feb 16, 2026
Best Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Best Score
InnoEval
Backbone=DeepSeek-V3.2
2026.02
65.12
ScholarEval
Backbone=DeepSeek-V3.2
2026.02
49.42
InternAgent
Backbone=DeepSeek-V3.2
2026.02
41.28
ResearchAgent
Backbone=DeepSeek-V3.2
2026.02
40.12
CoT
Backbone=DeepSeek-V3.2
2026.02
36.63
RAG
Backbone=DeepSeek-V3.2
2026.02
34.3
GraphEval
Backbone=DeepSeek-V3.2
2026.02
20.93
Feedback
Search any
task
Search any
task