Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Summarization Faithfulness Evaluation on 100 articles (Protocol 1)
Loading...
19
Llama-70B Faithfulness (%)
Claude-3.5
2.36
6.68
11
15.32
Jun 24, 2026
Llama-70B Faithfulness (%)
ALLaM Faithfulness (%)
Claude Faithfulness (%)
GPT-4o Faithfulness (%)
Jais-70B Faithfulness (%)
Mean Faithfulness (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Llama-70B Faithfulness (%)
ALLaM Faithfulness (%)
Claude Faithfulness (%)
GPT-4o Faithfulness (%)
Jais-70B Faithfulness (%)
Mean Faithfulness (%)
Claude-3.5
Generation Protocol=Pr...
2026.06
19
6
3
2
21
10.2
GPT-4o
Generation Protocol=Pr...
2026.06
19
3
1
0
30
10.6
Llama-70B
Generation Protocol=Pr...
2026.06
17
5
1
2
20
9
Jais-70B
Generation Protocol=Pr...
2026.06
12
7
7
3
5
6.8
Qwen2-72B
Generation Protocol=Pr...
2026.06
9
2
1
0
15
5.4
ALLaM
Generation Protocol=Pr...
2026.06
3
0
0
0
3
1.2
Feedback
Search any
task
Search any
task