Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Summarization Faithfulness Evaluation on FeedSum
Loading...
96
Consistency Score
Gemini
80.4
84.45
88.5
92.55
Apr 19, 2026
Consistency Score
Coherence Score
Balance Score
Average Faithfulness
Updated 1mo ago
Evaluation Results
Method
Method
Links
Consistency Score
Coherence Score
Balance Score
Average Faithfulness
Gemini
Evaluation framework=F...
2026.04
96
89
93
93
GPT4omini
Evaluation framework=F...
2026.04
95
93
93
94
GPT4-turbo
Evaluation framework=F...
2026.04
95
92
92
93
GPT4o
Evaluation framework=F...
2026.04
94
91
95
93
Mistral
Evaluation framework=F...
2026.04
91
89
90
90
Qwen
Evaluation framework=F...
2026.04
88
83
85
85
Qwen*
Evaluation framework=F...
2026.04
87
83
85
85
SummLLaMA
Evaluation framework=F...
2026.04
85
85
84
85
LLaMA*
Evaluation framework=F...
2026.04
85
80
80
82
LLaMA
Evaluation framework=F...
2026.04
83
83
80
82
Mistral*
Evaluation framework=F...
2026.04
81
82
80
81
Feedback
Search any
task
Search any
task