Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Claim Verification on FinDVer (test)
Loading...
76
Accuracy
Mistral-Large
57.28
62.14
67
71.86
Apr 19, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Mistral-Large
Parameters=123B
2026.04
76
GPT-4o
2026.04
76
MACE
Backbone=Qw-235B, Comp...
2026.04
76
Llama-3.1
Parameters=70B
2026.04
75
Qwen-2.5
Parameters=72B
2026.04
75
MACE
Backbone=Qw-72B, Compo...
2026.04
74
Gemini-1.5-Pro
2026.04
73
MACE
Backbone=Ll-8B, Compon...
2026.04
71
Qwen-2.5
2026.04
70
Claude-3.5-Sonnet
2026.04
70
MACE
Backbone=Mt-7B, Compon...
2026.04
65
DeepSeek-V2-Lite
2026.04
58
Feedback
Search any
task
Search any
task