Relationship Detection on TEA (test)
94Accuracyo3-2025
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| o3-20252026.02 | 94 | — | |
| Human2026.02 | 89 | — | |
| Claude-Opus-42026.02 | 87 | — | |
| Gemini-2.5-Flash2026.02 | 86 | — | |
| GPT-4.12026.02 | 85 | — | |
| GPT-4o2026.02 | 83 | — | |
| Gemini-2.5-Pro2026.02 | 83 | — | |
| llama-4-Scout2026.02 | 81 | — | |
| GPT-52026.02 | 80.5 | — |