Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text Generation on TruthfulQA (test)
Loading...
2.8
LCTG Error Rate
MARKERGEN
2.196
6.273
10.35
14.427
Feb 19, 2025
LCTG Error Rate
Text Quality Score
Token Cost
Updated 4d ago
Evaluation Results
Method
Method
Links
LCTG Error Rate
Text Quality Score
Token Cost
MARKERGEN
Backbone=Llama3.1-70B
2025.02
2.8
4.48
-
MARKERGEN
Backbone=Llama3.1-8B
2025.02
3.82
4.25
-
MARKERGEN
Backbone=Qwen2.5-32B
2025.02
4.48
4.54
-
Implicit
Backbone=Llama3.1-8B
2025.02
7.21
4.22
-
MARKERGEN
Backbone=Qwen2.5-14B
2025.02
7.59
4.43
-
Implicit
Backbone=Llama3.1-70B
2025.02
7.64
4.46
-
Implicit
Backbone=Qwen2.5-32B
2025.02
8.7
4.45
-
MARKERGEN
Backbone=Qwen2.5-7B
2025.02
9.08
4.33
-
Implicit
Backbone=Qwen2.5-7B
2025.02
16.7
4.29
-
Implicit
Backbone=Qwen2.5-14B
2025.02
17.9
4.44
-
Feedback
Search any
task
Search any
task
