Span-level Hallucination Detection on LettuceDetect Code-agent (test)
60.2F1 ScoreLettuceDetect-Qwen-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| LettuceDetect-Qwen-2B2026.07 | 60.2 | 59.6 | 60.9 | 83.5 | |
| LD-mmBERT2026.07 | 50.8 | — | — | — | |
| LFM-8B2026.07 | 50.7 | — | — | — | |
| gpt-oss2026.07 | 17.7 | — | — | — |