Human-AI Agreement Assessment on SSTEW 30
0.782Trust & Self-regulation KappaDeepSeek-v3.1
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-v3.12026.03 | 0.782 | 89.5 | 0.867 | 94.9 | 0.648 | 82.8 | 0.665 | 84.3 | 0.741 | 87.9 | |
| Qwen3-Max2026.03 | 0.763 | 90.3 | 0.825 | 91.3 | 0.627 | 81.5 | 0.65 | 83.1 | 0.716 | 86.6 | |
| GPT-52026.03 | 0.695 | 85.9 | 0.718 | 86.3 | 0.704 | 82 | 0.679 | 83.7 | 0.699 | 84.5 | |
| Gemini-2.5-pro2026.03 | 0.668 | 84.8 | 0.752 | 87.8 | 0.651 | 80.4 | 0.693 | 83.4 | 0.691 | 84.1 |