Share your thoughts, 1 month free Claude Pro on usSee more

Claim Verification on FinDVer mini (test)

76Accuracy

Qwen-2.5

Updated 1mo ago

Evaluation Results

Method	Links
Qwen-2.5 2026.04		76
MACE 2026.04		76
Llama-3.1 2026.04		75
Mistral-Large 2026.04		75
GPT-4o 2026.04		75
MACE 2026.04		75
Claude-3.5-Sonnet 2026.04		73
Qwen-2.5 2026.04		72
Gemini-1.5-Pro 2026.04		71
MACE 2026.04		68
MACE 2026.04		64
DeepSeek-V2-Lite 2026.04		60