Google DeepMind
gemini-2.5-pro-preview-05-06
Made by Google DeepMind. Released 2025-05-06. Accessibility not recorded. We hold no price for this model: no seller we can read lists it any more, so what follows is what was measured, not what it cost.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| gpqa diamond | Epoch AI | 0.7±0.03 | 2025-06-03 | — |
| math level 5near its ceiling | Epoch AI | 1.0±0.00 | 2025-05-08 | — |
| aider polyglot | collected by Epoch AI | 76.9 | — | — |
| enigma eval | collected by Epoch AI | 0.0 | — | — |
| fictionlivebench | collected by Epoch AI | 0.7 | — | — |
| geobench | collected by Epoch AI | 3983 | — | Search |
| geobench | collected by Epoch AI | 4085 | — | — |
| hle | collected by Epoch AI | 0.2 | — | — |
| lech mazur writing | collected by Epoch AI | 8.1 | — | — |
| the agent company | collected by Epoch AI | 0.4 | — | — |
| vpct | collected by Epoch AI | 0.4 | — | — |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.