Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact-claim Decomposition on SocialClaimSplit-100 1.0 (test)
Loading...
99.3
Semantic F1
CREDENCE-base
80.372
85.286
90.2
95.114
Jun 18, 2026
Semantic F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Semantic F1
CREDENCE-base
Model=Gemini Flash
2026.06
99.3
CREDENCE-all
Model=Gemini Flash
2026.06
99.2
FActScore-prompt
Model=Gemma-3-12b
2026.06
98.2
FActScore-prompt
Model=Gemini Flash
2026.06
97.5
CREDENCE-all
Model=Qwen3-8B
2026.06
97.3
FActScore-prompt
Model=Qwen3-8B
2026.06
96.9
CREDENCE-all
Model=Gemma-3-12b
2026.06
95.9
CREDENCE-base
Model=Gemma-3-12b
2026.06
95.7
CREDENCE-base
Model=Qwen3-8B
2026.06
95.6
CREDENCE-base
Model=Phi-3-mini
2026.06
93
CREDENCE-all
Model=Phi-3-mini
2026.06
92.2
FActScore-prompt
Model=Phi-3-mini
2026.06
87.1
SpaCy-senter
Model=Phi-3-mini
2026.06
81.1
SpaCy-senter
Model=Qwen3-8B
2026.06
81.1
SpaCy-senter
Model=Gemma-3-12b
2026.06
81.1
SpaCy-senter
Model=Gemini Flash
2026.06
81.1
Feedback
Search any
task
Search any
task