Human-AI Agreement Assessment on ECQRS-EC 34
0.764Literacy KappaQwen3-Max
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Qwen3-Max2026.03 | 0.764 | 88.2 | 0.656 | 85.3 | 0.611 | 83.6 | 0.677 | 85.7 | |
| Gemini-2.5-pro2026.03 | 0.736 | 87.1 | 0.659 | 84.5 | 0.591 | 85.2 | 0.662 | 85.6 | |
| DeepSeek-v3.12026.03 | 0.705 | 88.6 | 0.721 | 87.6 | 0.704 | 85.8 | 0.71 | 87.3 | |
| GPT-52026.03 | 0.678 | 84.4 | 0.631 | 83.6 | 0.605 | 82.3 | 0.638 | 83.4 |