Model comparison
Lift vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
Lift
Not scored
value score
Gemini 2.5 Pro
93
value score
Lift 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 | Lift | Gemini 2.5 Pro |
|---|---|---|
| Developer | KCB1 | 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 | Lift is a vision-language model designed to parse complex documents—combining text and images—and reconstruct their structure (headings, tables, figures, formulas, reading order) into machine-readable, structured outputs. It supports GGUF quantization for efficient local inference via llama.cpp. | Google frontier multimodal model. |