Classification on ODD-TAX-232
73Overall AccuracyGemini 2.5 Pro
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Gemini 2.5 ProZero-shot=true2026.05 | 73 | 72 | 75 | 72 | 72 | 69 | |
| GPT-4oZero-shot=true2026.05 | 72 | 68 | 74 | 74 | 69 | 72 | |
| MaverickZero-shot=true2026.05 | 67 | 62 | 68 | 67 | 65 | 77 | |
| Molmo-72BZero-shot=true2026.05 | 45 | 46 | 51 | 57 | 26 | 32 |