Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Fact-checking on AggreFact CNN
Loading...
69.5
Balanced Acc
GraphEval
44.332
50.866
57.4
63.934
Feb 23, 2025
Balanced Acc
Updated 4d ago
Evaluation Results
Method
Method
Links
Balanced Acc
GraphEval
2025.02
69.5
Claude 3.5-Sonnet
Scale=>300B
2025.02
68.8
GPT-4o
Scale=>300B
2025.02
66.8
GraphCheck
Backbone=Qwen 72B
2025.02
66.5
OpenAI o1
Scale=>300B
2025.02
65.3
MiniCheck
2025.02
63.7
DeepSeek-V3 671B
Scale=>300B
2025.02
63.2
GraphCheck
Backbone=Llama3.3 70B
2025.02
62.4
GPT-4
Scale=>300B
2025.02
60.7
AlignScore
2025.02
54.1
Llama3.3 70B
2025.02
53.5
Llama3 8B
2025.02
51.3
ACUEval
2025.02
50
Qwen2.5 72B
2025.02
49.9
Qwen2.5 7B
2025.02
45.3
Feedback
Search any
task
Search any
task