Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Narrative Reasoning on BookSum oracle timing
Loading...
94
Average Score
CFPG
46.264
58.657
71.05
83.443
Jan 11, 2026
Average Score
Should Payoff Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score
Should Payoff Rate
CFPG
Base Model=Claude-Haik...
2026.01
94
96.5
CFPG
Base Model=GPT-4.1-min...
2026.01
91.1
100
CFPG
Base Model=Qwen2.5-14B...
2026.01
89.8
100
CFPG
Base Model=Llama-3.1-8...
2026.01
80.2
100
CFPG
Base Model=Qwen2.5-7B,...
2026.01
79.7
100
CFPG
Base Model=Qwen2.5-3B,...
2026.01
78.1
99.8
Prompt
Base Model=Claude-Haik...
2026.01
65.7
-
Prompt
Base Model=Qwen2.5-14B...
2026.01
58.3
-
Prompt
Base Model=GPT-4.1-min...
2026.01
56.9
-
Prompt
Base Model=Llama-3.1-8...
2026.01
53
-
Prompt
Base Model=Qwen2.5-7B,...
2026.01
51.7
-
Prompt
Base Model=Qwen2.5-3B,...
2026.01
48.1
-
Feedback
Search any
task
Search any
task
