Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Opinion Summarization on SPACE
Loading...
100
Coverage
Aspect-aware decomposition
34.48
51.49
68.5
85.51
Mar 1, 2026
Coverage
G-Eval Score
AlignScore-R
AlignScore-M
Updated 27d ago
Evaluation Results
Method
Method
Links
Coverage
G-Eval Score
AlignScore-R
AlignScore-M
Aspect-aware decomposition
Base Model=GPT-4o
2026.03
100
90
81
10
MOSAIC
Base Model=GPT-4o
2026.03
100
90
77
7
Aspect-aware decomposition
Base Model=Llama 70B
2026.03
99
88
79
11
MOSAIC
Base Model=Llama 70B
2026.03
99
88
86
16
TCG
2026.03
98
66
66
11
Chunk-wise decomposition
Base Model=Llama 70B
2026.03
93
84
65
1
HIRO-abs
2026.03
87
62
83
24
Automatic decomposition
Base Model=Llama 70B
2026.03
63
38
70
22
Naive aspect-aware prompting
Base Model=Llama 70B
2026.03
37
34
44
22
Feedback
Search any
task
Search any
task