Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Consistency Evaluation on Q-Reasoning (test)
Loading...
51.4
ROUGE-1 Score
Proposed Human-Like Reasoning Framework (detailed)
26.96
33.305
39.65
45.995
Dec 18, 2025
ROUGE-1 Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
ROUGE-1 Score
Proposed Human-Like Reasoning Framework (detailed)
prompt_template=(c) De...
2025.12
51.4
Proposed Human-Like Reasoning Framework (base)
prompt_template=(b) Ba...
2025.12
51.2
Q-Insight
training=RL-based, var...
2025.12
48.7
Q-Insight-Score
prompt_template=(a) Ba...
2025.12
44.3
DepictQA
training=SFT-based
2025.12
31.8
Q-Instruct
training=SFT-based
2025.12
27.9
Feedback
Search any
task
Search any
task