Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theme Detection on DSTC Travel domain 12 (test)
Loading...
89.7
Semantic Relevance (SR)
Team C
43.42
55.435
67.45
79.465
Dec 25, 2025
Semantic Relevance (SR)
Analytical Utility (AU)
Granularity (GR)
Actionability (ACT)
Domain Relevance (DR)
Conciseness & Word Choice (CWC)
Grammatical Structure (GS)
Thematic Distinctiveness (TD)
Overall Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Semantic Relevance (SR)
Analytical Utility (AU)
Granularity (GR)
Actionability (ACT)
Domain Relevance (DR)
Conciseness & Word Choice (CWC)
Grammatical Structure (GS)
Thematic Distinctiveness (TD)
Overall Average Score
Team C
2025.12
89.7
82.8
47.8
74.8
98.8
100
100
91.1
85.6
CATCH
Team ID=Team E
2025.12
86.2
54.6
22.5
54.5
91.1
93.7
93.7
78.3
71.8
Team A
2025.12
77.3
63.7
22.8
56.2
79.8
83.3
100
75.8
69.8
Team D
2025.12
68.8
63.7
26.4
60.3
94.3
91.7
66.7
90.9
70.3
Team B
2025.12
65
12.9
0
4.1
97.8
100
33.3
0
39.1
Team F
2025.12
45.2
41.6
7.7
41.6
67.5
95
100
72.6
58.9
Feedback
Search any
task
Search any
task
