Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Summarization on SummaryBench Dynasts
Loading...
99.7
Structural Score
APWA
18.06
39.255
60.45
81.645
May 14, 2026
Structural Score
Semantic Score
Fidelity Score (FR)
Processing Time (s)
Updated 19d ago
Evaluation Results
Method
Method
Links
Structural Score
Semantic Score
Fidelity Score (FR)
Processing Time (s)
APWA
Config=5.4×mini
2026.05
99.7
45.1
-
-
Direct
LLM Backend=GPT-5.4 mini
2026.05
97.9
21
-
-
Direct
2026.05
97.9
21
-
-
APWA
Config=mini×mini
2026.05
97.1
44.7
-
-
APWA
LLM Backend=GPT-5.4 mini
2026.05
95.4
41.9
-
-
APWA
Config=5.4×nano
2026.05
92.3
41.9
-
-
APWA
Config=mini×nano
2026.05
87.2
32.3
-
-
MegaAgent
LLM Backend=GPT-4.1 mini
2026.05
21.2
2.3
-
-
MegaAgent
2026.05
21.2
2.3
-
-
Direct
LLM Backend=GPT-5.4 mini
2026.05
-
-
60
76
Magentic-One
LLM Backend=GPT-5.4 mini
2026.05
-
-
100
-
MegaAgent
LLM Backend=GPT-4.1 mini
2026.05
-
-
80
248
APWA
LLM Backend=GPT-5.4 mini
2026.05
-
-
0
210
Feedback
Search any
task
Search any
task
