Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logical Reasoning on ProofWriter (Acc, TTFT, Delay (s))
Loading...
81.3
Accuracy
StreamingThinker
57.38
63.59
69.8
76.01
Oct 20, 2025
Accuracy
TTFT
Delay (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
TTFT
Delay (s)
StreamingThinker
Paradigm=Streaming, Re...
2025.10
81.3
20.51
11.05
Interleaved
Paradigm=Interleaved,...
2025.10
80.1
20.51
22.35
StreamingThinker
Paradigm=Streaming, Re...
2025.10
76.1
20.51
6.5
Interleaved
Paradigm=Interleaved,...
2025.10
75
20.51
18.07
Batch
Paradigm=Batch, Model=...
2025.10
62
232.11
61.99
StreamingThinker
Paradigm=Streaming, Re...
2025.10
58.8
20.51
0.71
Interleaved
Paradigm=Interleaved,...
2025.10
58.3
20.51
11.96
Feedback
Search any
task
Search any
task