Binary Classification on Turing Test Human-Machine
97.22Accuracyinterpretable AI judge
Evaluation Results
| Method | Links | |
|---|---|---|
| interpretable AI judge2026.02 | 97.22 | |
| Human Judge2026.02 | 83.57 | |
| Qwen2.5-OmniFine-tuned=LoRA2026.02 | 63.19 | |
| Qwen2.5-Omni2026.02 | 23.61 |
Loading the SOTA2 catalog…