Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Source Coverage Evaluation on DIVERSESUMM 1.0 (test)
Loading...
59.23
Source Coverage
LLM + DPP
22.8716
32.3108
41.75
51.1892
May 28, 2025
Source Coverage
Updated 5mo ago
Evaluation Results
Method
Method
Links
Source Coverage
LLM + DPP
LLM=Claude-3-Sonnet
2025.05
59.23
LLM + DPP
LLM=GPT-4o
2025.05
58.05
LLM-Selected KPs
LLM=GPT-4o
2025.05
57.47
All KPs
LLM=Claude-3-Sonnet
2025.05
56.83
Naive LLM
LLM=GPT-4o
2025.05
55.16
All KPs
LLM=GPT-4o
2025.05
54.43
LLM-Selected KPs
LLM=Claude-3-Sonnet
2025.05
53.69
Naive LLM
LLM=Claude-3-Sonnet
2025.05
47.76
LLM + DPP
LLM=GPT-3.5
2025.05
47.06
LLM-Selected KPs
LLM=GPT-3.5
2025.05
43.7
LLM + DPP
LLM=Llama-3.1
2025.05
36.53
All KPs
LLM=GPT-3.5
2025.05
34.72
All KPs
LLM=Llama-3.1
2025.05
34.58
LLM-Selected KPs
LLM=Llama-3.1
2025.05
33.76
Naive LLM
LLM=GPT-3.5
2025.05
33.24
Naive LLM
LLM=Llama-3.1
2025.05
24.27
Feedback
Search any
task
Search any
task