Gemini 2.5 Computer Use Preview

Tool callingReasoningImage input

Launch post Website Docs

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

Context: 128K
Released: 1y ago

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Google DeepMind
Model family: Gemini
Type: Language model
Predecessor: —
Successor: —
Released: October 7, 2025
Model ID: google/gemini-2.5-computer-use-preview-10-2025
Openness: Closed
License: —
Input modalities: text, image
Output modalities: text
Modality: text+image->text
Max output tokens: 64K
Knowledge cutoff: 2025-01
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: google/gemini-2.5-computer-use-preview-10-2025
Source family: gemini-pro
Last updated: 2025-10-07
Knowledge cutoff: 2025-01
Model context: 128K
Model output limit: 64K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Complete source record (JSON)

{
  "id": "google/gemini-2.5-computer-use-preview-10-2025",
  "name": "Gemini 2.5 Computer Use Preview",
  "description": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks",
  "family": "gemini-pro",
  "last_updated": "2025-10-07",
  "knowledge": "2025-01",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 128000,
    "output": 64000
  },
  "release_date": "2025-10-07",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider endpoint data will appear after this model's first OpenRouter endpoint sync.

Text provenance

Gemini app/web

Google SynthID text watermarking

Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.

Official explanation