Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Caption Generation on Electronic Sheep
Loading...
72
1-gram Overlap
HOMER
57.44
61.22
65
68.78
Feb 6, 2026
1-gram Overlap
2-gram Overlap
3-gram Overlap
NLI Diversity
Updated 1mo ago
Evaluation Results
Method
Method
Links
1-gram Overlap
2-gram Overlap
3-gram Overlap
NLI Diversity
HOMER
2026.02
72
94
98
92.2
HumorousAI
2026.02
65
87
92
88.5
Phunny
2026.02
64
84
89
85.2
LoL
2026.02
63
88
94
91.9
CLoT
2026.02
58
78
83
78.9
Feedback
Search any
task
Search any
task