List your company

Span-level Hallucination Detection on LettuceDetect Code-agent (test)

60.2F1 ScoreLettuceDetect-Qwen-2B
1627.47538.9550.425Jul 1, 2026

Evaluation results

MethodLinks
LettuceDetect-Qwen-2B2026.0760.259.660.983.5
LD-mmBERT2026.0750.8———
LFM-8B2026.0750.7———
gpt-oss2026.0717.7———