Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Model Fingerprinting on System Prompt Variations
Loading...
96
Fastchat Score
Base+S2.7-P+[D+Z]
-3.84
22.08
48
73.92
May 8, 2025
Fastchat Score
Llama2 Score
OpenAI Score
Hiking Score
Tax Score
Json Score
Mktg Score
Shake Score
Cust Score
Updated 6d ago
Evaluation Results
Method
Method
Links
Fastchat Score
Llama2 Score
OpenAI Score
Hiking Score
Tax Score
Json Score
Mktg Score
Shake Score
Cust Score
Base+S2.7-P+[D+Z]
Task Combination=Base+...
2025.05
96
84
90
88
72
86
90
82
86
Base+Chat Template
Task Combination=Base+...
2025.05
54
47
72
53
26
48
52
38
45
Base+Homologous Model
Task Combination=Base+...
2025.05
39
30
56
34
22
33
37
30
35
Base (64)
Task Combination=Base...
2025.05
22
22
48
32
18
20
24
20
30
Base (32)
Task Combination=Base...
2025.05
16
10
26
14
8
10
10
14
10
Base+Non-Homologous Model
Task Combination=Base+...
2025.05
0
0
0
0
2
0
2
2
0
Feedback
Search any
task
Search any
task