Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact-claim Decomposition on ClaimDecompBench 1.0 (test)
Loading...
84.2
Semantic F1
CREDENCE-base
77.232
79.041
80.85
82.659
Jun 18, 2026
Semantic F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Semantic F1
CREDENCE-base
Model=Qwen3-8B
2026.06
84.2
CREDENCE-all
Model=Qwen3-8B
2026.06
83.9
CREDENCE-base
Model=Gemma-3-12b
2026.06
83.9
CREDENCE-all
Model=Gemma-3-12b
2026.06
83.9
CREDENCE-base
Model=Phi-3-mini
2026.06
82.6
CREDENCE-all
Model=Phi-3-mini
2026.06
82.6
CREDENCE-all
Model=Gemini Flash
2026.06
81.8
SpaCy-senter
Model=Phi-3-mini
2026.06
81.4
SpaCy-senter
Model=Qwen3-8B
2026.06
81.4
SpaCy-senter
Model=Gemma-3-12b
2026.06
81.4
SpaCy-senter
Model=Gemini Flash
2026.06
81.4
FActScore-prompt
Model=Qwen3-8B
2026.06
81.2
CREDENCE-base
Model=Gemini Flash
2026.06
81.1
FActScore-prompt
Model=Gemini Flash
2026.06
79
FActScore-prompt
Model=Phi-3-mini
2026.06
77.8
FActScore-prompt
Model=Gemma-3-12b
2026.06
77.5
Feedback
Search any
task
Search any
task