Model comparison
Gemini 2.5 Pro Preview 06-05 vs o3
Capability radar, value bars, and side-by-side posture.
Gemini 2.5 Pro Preview 06-05
Not scored
value score
o3
93
value score
Gemini 2.5 Pro Preview 06-05 ctx
1.0M
o3 ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- o393
Attribute tape
| Field | Gemini 2.5 Pro Preview 06-05 | o3 |
|---|---|---|
| Developer | Google AI | OpenAI |
| Context | 1.0M | 200K |
| Modalities | Text, Code | |
| Openness | Closed | Proprietary Model |
| Speed | — | — |
| Price | $1.25/1M in · $10/1M out | $10/1M in · $40/1M out |
| Value score | — | 93 |
| Summary | Gemini 2.5 Pro Preview 06-05 is Google's preview release of its most capable multimodal reasoning model, designed for complex coding, analysis, and agentic tasks with a 1M-token context window. It fed into the Gemini 2.5 Pro stable release (GA June 17, 2025), with the preview endpoint now redirecting to the stable model. | OpenAI reasoning model focused on hard problems. |