Model comparison
RoboMME Model vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
RoboMME Model
Not scored
value score
Gemini 2.5 Pro
93
value score
RoboMME Model ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | RoboMME Model | Gemini 2.5 Pro |
|---|---|---|
| Developer | Mode | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | RoboMME is a research benchmark and associated model for evaluating vision-language-action (VLA) models on memory-augmented robotic manipulation tasks. It tests how well robot AI systems remember object state, spatial layout, and task history across long-horizon manipulation sequences. | Google frontier multimodal model. |