List your company

Span-level Hallucination Detection on LettuceDetect (test)

86.6F1 ScoreLettuceDetect-Qwen-2B
30.9645.40559.8574.295Jul 1, 2026

Evaluation results

MethodLinks
LettuceDetect-Qwen-2B2026.0786.688.984.498.4
LFM-8B2026.0780.4———
LD-mmBERT2026.0775.1———
LettuceDetect-Qwen-2B2026.0774.975.274.594.2
LettuceDetect-Qwen-2B2026.0771.973.770.290.7
LFM-8B2026.0769.2———
LFM-8B2026.0767———
gpt-oss2026.0766.6———
gpt-oss2026.0760.2———
LD-mmBERT2026.0758.8———
LD-mmBERT2026.0757.9———
gpt-oss2026.0733.1———