Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific question generation on ICLR papers 2024 (test)
Loading...
0.54
Effectiveness
Human questions
-0.0008
0.1396
0.28
0.4204
Jan 23, 2026
Effectiveness
Evidence
Groundedness
Total Score
FPB (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Effectiveness
Evidence
Groundedness
Total Score
FPB (%)
Human questions
Reasoning Mode=Not App...
2026.01
0.54
0.46
0.57
1.57
28.21
o3
Reasoning Mode=Medium
2026.01
0.32
0.12
0.36
0.8
16.81
IntelliAsk-32B
Reasoning Mode=Default
2026.01
0.27
0.13
0.26
0.66
21.37
Gemini 2.5 Pro
Reasoning Mode=Default
2026.01
0.26
0.13
0.21
0.6
25.75
Qwen2.5-32B
Reasoning Mode=No reas...
2026.01
0.02
0.01
0.02
0.05
54.96
Feedback
Search any
task
Search any
task