Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Reasoning Efficiency on LongBench
Loading...
1
Relative Cost
CoT
0.7176
2.6238
4.53
6.4362
Mar 13, 2026
Relative Cost
Token Consumption
Updated 11d ago
Evaluation Results
Method
Method
Links
Relative Cost
Token Consumption
CoT
Evaluation Model=GPT-4...
2026.03
1
78
Analogical Prompting
Evaluation Model=GPT-4...
2026.03
1.01
-
TDA-RC
Evaluation Model=GPT-4...
2026.03
1.1
-
Role / Persona Prompting
Evaluation Model=GPT-4...
2026.03
1.12
-
Instruction Induction
Evaluation Model=GPT-4...
2026.03
1.13
-
Prompt Canvas
Evaluation Model=GPT-4...
2026.03
1.15
-
HoT
Evaluation Model=GPT-4...
2026.03
1.19
-
Self-Refine
Evaluation Model=GPT-4...
2026.03
2.46
-
AoT
Evaluation Model=GPT-4...
2026.03
3.37
-
AFlow
Evaluation Model=GPT-4...
2026.03
4.14
-
CoT-SC
Evaluation Model=GPT-4...
2026.03
4.97
-
ToT
Evaluation Model=GPT-4...
2026.03
6.08
-
GoT
Evaluation Model=GPT-4...
2026.03
6.49
-
FoT
Evaluation Model=GPT-4...
2026.03
8.06
-
Feedback
Search any
task
Search any
task