List your company

Fact-checking on FeLMWk

0.79F1 (True)PCC
0.46760.55130.6350.7187Jan 5, 2026

Evaluation results

MethodLinks
PCCLLM=GPT-4o2026.010.790.68
PCCLLM=Gemini-2.5-Pro2026.010.770.74
FIRELLM=GPT-4o2026.010.770.63
PCCLLM=Gemini-2.5-Flash2026.010.760.72
PCCLLM=GPT-4o-mini2026.010.760.6
SAFELLM=GPT-4o2026.010.750.65
FIRELLM=Gemini-2.5-Pro2026.010.740.71
FIRELLM=Gemini-2.5-Flash2026.010.730.7
FIRELLM=GPT-4o-mini2026.010.710.53
SAFELLM=GPT-4o-mini2026.010.680.51
Factcheck-GPTLLM=GPT-4o2026.010.670.61
PCCLLM=Mistral-7B-Instruct2026.010.60.55
FactoolLLM=GPT-4o2026.010.60.64
FIRELLM=Mistral-7B-Instruct2026.010.560.52
Factcheck-GPTLLM=GPT-4o-mini2026.010.550.56
FactoolLLM=GPT-4o-mini2026.010.480.62