Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Fact Verification on VitaminC (Accuracy and Latency)
Loading...
54
Accuracy (%)
CPO
45.992
48.071
50.15
52.229
Jun 13, 2024
Accuracy (%)
Latency (s/ins.)
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
Latency (s/ins.)
CPO
Backbone=LLAMA2-13B
2024.06
54
58.6
CPO
Backbone=Mistral-7B
2024.06
53.7
46.6
CPO
Backbone=LLAMA2-7B
2024.06
52.7
40.1
ToT
Backbone=LLAMA2-13B
2024.06
52.5
2,933.6
ToT
Backbone=Mistral-7B
2024.06
52.2
4,698.2
TS-SFT
Backbone=LLAMA2-7B
2024.06
51
40.1
ToT
Backbone=LLAMA2-7B
2024.06
50.7
2,639.3
TS-SFT
Backbone=Mistral-7B
2024.06
50.3
45.9
TS-SFT
Backbone=LLAMA2-13B
2024.06
49.7
51.5
CoT
Backbone=Mistral-7B
2024.06
47.7
44.8
CoT
Backbone=LLAMA2-7B
2024.06
47.3
35.9
CoT
Backbone=LLAMA2-13B
2024.06
46.3
48.3
Feedback
Search any
task
Search any
task