Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Summarization on SummaryBench Roman
Loading...
91.9
Structural Score
APWA
-3.5096
21.2602
46.03
70.7998
May 14, 2026
Structural Score
Semantic Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Structural Score
Semantic Score
APWA
LLM Backend=GPT-5.4 mini
2026.05
91.9
23.2
MegaAgent
LLM Backend=GPT-4.1 mini
2026.05
16
1.6
APWA
Config=5.4×mini
2026.05
0.983
0.37
APWA
Config=mini×nano
2026.05
0.914
0.295
APWA
Config=mini×mini
2026.05
0.908
0.23
APWA
Config=5.4×nano
2026.05
0.872
0.395
MegaAgent
2026.05
0.16
0.016
Feedback
Search any
task
Search any
task
