Span-level Hallucination Detection on LettuceDetect Code-agent (test)
60.2F1 Score
LettuceDetect-Qwen-2B
Updated 23d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.07 | 60.2 | 59.6 | 60.9 | 83.5 | |
2026.07 | 50.8 | - | - | - | |
2026.07 | 50.7 | - | - | - | |
2026.07 | 17.7 | - | - | - |
LettuceDetect-Qwen-2B
| Method | Links | ||||
|---|---|---|---|---|---|
2026.07 | 60.2 | 59.6 | 60.9 | 83.5 | |
2026.07 | 50.8 | - | - | - | |
2026.07 | 50.7 | - | - | - | |
2026.07 | 17.7 | - | - | - |