Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Research Automation on Three real research tasks Human researcher evaluation
Loading...
9.333
Alignment
NanoResearch
4.133
5.483
6.833
8.183
May 11, 2026
Alignment
Novelty
E2E Capability
Performance Score
Writing Quality Score
Updated 22d ago
Evaluation Results
Method
Method
Links
Alignment
Novelty
E2E Capability
Performance Score
Writing Quality Score
NanoResearch
Round=1
2026.05
9.333
6
1
64.66
7
NanoResearch
Round=2
2026.05
9.333
7
1
85.02
8
NanoResearch
Round=3
2026.05
9.333
6.667
1
86.03
7.667
DeepScientist
2026.05
6.333
5
1
60.94
5.333
EvoScientist
2026.05
6
4.667
1
65.37
4
AI Scientist-v2
2026.05
5.333
4
1
49.65
4.333
AI-Researcher
2026.05
4.333
3.333
1
54.95
4.667
Feedback
Search any
task
Search any
task