Rule-based evaluation of diagram components on Molmo
60.8R
GPT-5.2
Updated 23d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 60.8 | 37.9 | 83.7 | |
2026.03 | 58 | 35.3 | 80.6 | |
2026.03 | 55.5 | 33.2 | 77.7 | |
2026.03 | 35.9 | 21.9 | 49.9 | |
2026.03 | 35.4 | 0 | 70.7 |
GPT-5.2
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 60.8 | 37.9 | 83.7 | |
2026.03 | 58 | 35.3 | 80.6 | |
2026.03 | 55.5 | 33.2 | 77.7 | |
2026.03 | 35.9 | 21.9 | 49.9 | |
2026.03 | 35.4 | 0 | 70.7 |