GPT-5 Computer Use

GPT-5.4, released by OpenAI on March 5, 2026, is the first general-purpose AI model with native computer-use capabilities — the ability to see a screen, move a cursor, click, type, and execute multi-step workflows without wrapper code or external tools. It scored 75.0% on OSWorld-Verified, surpassing the human expert baseline of 72.4%, making it the strongest computer-operating AI model available. ¹⁾

GPT-5 was first released on August 7, 2025, as OpenAI's flagship multimodal model excelling in coding, math, writing, and visual perception. ²⁾ The computer-use capability arrived with the GPT-5.4 update on March 5, 2026, representing what many analysts consider OpenAI's most significant product advancement since the original ChatGPT launch.

Unlike previous browser-automation approaches that relied on brittle scripts or browser-specific APIs, GPT-5.4 operates at the visual level:

1. The model receives screenshots of the current screen state
2. It decides what to click, type, or interact with
3. It executes the action via mouse/keyboard commands
4. It observes the result and continues the loop until the task is complete

The key innovation is that GPT-5.4 was trained end-to-end for computer use tasks — the capability is built into the model weights, not added as a plugin or post-training layer. The model supports both Playwright code generation for browser automation and direct mouse/keyboard commands from screenshots. ³⁾

• OSWorld-Verified: 75.0% (human baseline: 72.4%) — a 27.7 percentage-point improvement over GPT-5.2 ⁴⁾
• GDPval Score: 83.0% — matches or exceeds industry professionals across 44 occupations in the top 9 U.S. GDP-contributing industries ⁵⁾
• Context window: 1 million tokens
• Hallucination reduction: 33% fewer false claims vs GPT-5.2
• Tool Search: New API feature reduces token usage by 47% with zero accuracy loss

Anthropic introduced computer use for Claude in October 2024, establishing the category. Key differences:

• Anthropic's approach: Screenshot-based cursor movement, clicking, and typing via API, initially in beta with Claude 3.5 Sonnet
• OpenAI's approach: End-to-end trained capability baked into the model, supporting both visual (screenshot) and programmatic (Playwright) modes
• Performance gap: GPT-5.4's 75.0% OSWorld score surpasses all prior models including Claude's computer use implementations

GPT-5.4 is available in three configurations:

• GPT-5.4 Standard — available in ChatGPT for Plus, Team, and Pro subscribers
• GPT-5.4 Thinking — extended reasoning variant replacing GPT-5.2 Thinking
• GPT-5.4 Pro — maximum performance variant for ChatGPT Pro ($200/month) and API use

• Input: $2.50 per million tokens
• Context over 272K tokens: Billed at 2x normal rate
• Available via ChatGPT, OpenAI API (model ID: gpt-5.4), and Codex ⁶⁾

• OpenAI
• Computer Use
• AI Agents