Binary Classification on Turing Test (Overall)
96.05Accuracyinterpretable AI judge
Evaluation Results
| Method | Links | |
|---|---|---|
| interpretable AI judge2026.02 | 96.05 | |
| Human Judge2026.02 | 72.84 | |
| Qwen2.5-OmniFine-tuned=LoRA2026.02 | 57.44 | |
| Qwen2.5-Omni2026.02 | 41.63 |
Loading the SOTA2 catalog…