Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Representation Accuracy on Task Vector Evaluation Suite Llama2-13B (test)
Loading...
87.69
Accuracy
LTV
-2.2388
21.1081
44.455
67.8019
Sep 29, 2025
Accuracy
Updated 6d ago
Evaluation Results
Method
Method
Links
Accuracy
LTV
Injection Scenario=2)...
2025.09
87.69
LTV
Injection Scenario=5)...
2025.09
84.99
LTV
Injection Scenario=3)...
2025.09
82.25
LTV
Injection Scenario=Bas...
2025.09
80.33
FV
Injection Scenario=5)...
2025.09
77.51
LTV
Injection Scenario=1)...
2025.09
71.53
LTV
Injection Scenario=4)...
2025.09
51.46
Vanilla TV
Injection Scenario=5)...
2025.09
43.84
FV
Injection Scenario=2)...
2025.09
42.25
FV
Injection Scenario=Bas...
2025.09
41.59
FV
Injection Scenario=3)...
2025.09
36.97
Vanilla TV
Injection Scenario=Bas...
2025.09
27.67
FV
Injection Scenario=4)...
2025.09
24.74
Vanilla TV
Injection Scenario=3)...
2025.09
20.46
Vanilla TV
Injection Scenario=2)...
2025.09
16.42
Vanilla TV
Injection Scenario=4)...
2025.09
16.07
Vanilla TV
Injection Scenario=1)...
2025.09
1.84
FV
Injection Scenario=1)...
2025.09
1.22
Feedback
Search any
task
Search any
task