Domain Knowledge Estimation on Domain Knowledge Estimation Dataset
21.13MAEgemini-2.5-flash
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| gemini-2.5-flash2026.05 | 21.13 | 19.14 | 28.48 | 15 | |
| gemini-2.5-pro2026.05 | 22.68 | 21.52 | 31.23 | 16.5 | |
| claude-haiku-4-52026.05 | 26.74 | 22.41 | 34.85 | 25 | |
| claude-sonnet-4-52026.05 | 27.95 | 22.27 | 35.7 | 25 | |
| gpt-52026.05 | 32.7 | 26.83 | 42.26 | 28.5 | |
| gpt-o32026.05 | 32.71 | 26.55 | 42.09 | 28.5 | |
| gpt-4o2026.05 | 33.38 | 25.24 | 41.81 | 30 |