Diagnostic Reasoning on NOVA
24.2Top-1 AccuracyGemini 2.0 Flash
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini 2.0 FlashInformation Setting=Reported2026.05 | 24.2 | 38.4 | |
| Gemini 2.5 FlashInformation Setting=Croissant Tasks Only2026.05 | 19.75 | 40.8 | |
| Gemini 2.5 FlashInformation Setting=PDF Only2026.05 | 15.5 | 21.96 |