Hallucination Detection on FRANK
77.2Balanced AccInFi-Checker-Qwen
Evaluation Results
| Method | Links | |
|---|---|---|
| InFi-Checker-Qwenshot=0-shot2026.01 | 77.2 | |
| InFi-Checker-Llamashot=0-shot2026.01 | 77.17 | |
| DeepSeek-V3.2-NoThinkshot=1-shot2026.01 | 77.14 | |
| GPT-5shot=0-shot2026.01 | 76.53 | |
| GPT-5shot=1-shot2026.01 | 75.7 | |
| o3shot=0-shot2026.01 | 75.54 | |
| GPT-4.1shot=0-shot2026.01 | 75.19 | |
| GPT-4.1shot=1-shot2026.01 | 75.19 | |
| GPT-4oshot=1-shot2026.01 | 74.75 | |
| o3shot=1-shot2026.01 | 74.57 | |
| GPT-4oshot=0-shot2026.01 | 74.37 | |
| Llama-3.1-8B-Instructshot=1-shot2026.01 | 71.49 | |
| Qwen3-8Bshot=1-shot2026.01 | 70.16 | |
| DeepSeek-V3.2-NoThinkshot=0-shot2026.01 | 66.99 | |
| Llama-3.1-8B-Instructshot=0-shot2026.01 | 66.13 | |
| Claude-3.7-Sonnetshot=0-shot2026.01 | 65.89 | |
| Qwen3-8Bshot=0-shot2026.01 | 65.31 | |
| Claude-3.7-Sonnetshot=1-shot2026.01 | 63.42 |