GPT-5.4 vs GPT-5.2 Comparison
Performance Benchmarks
Comparative analysis across standard metrics
GPT-5.4 outperforms in 11 benchmarks (ARC-AGI, ARC-AGI v2, BrowseComp, FrontierMath, GPQA, Graphwalks parents <128k, Humanity's Last Exam, MCP Atlas, MMMU-Pro, Tau2 Telecom, Toolathlon), while GPT-5.2 is better at 1 benchmark (Graphwalks BFS <128k).
GPT-5.4 significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, GPT-5.4 ($2.50/1M tokens) is 1.4x more expensive than GPT-5.2 ($1.75/1M tokens).
For output processing, GPT-5.4 ($15.00/1M tokens) is 1.1x more expensive than GPT-5.2 ($14.00/1M tokens).
In conclusion, GPT-5.4 is more expensive than GPT-5.2.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
GPT-5.4 accepts 1,000,000 input tokens compared to GPT-5.2's 400,000 tokens. Both models can generate responses up to 128,000 tokens.
Input Capabilities
Supported data types and modalities
Both GPT-5.4 and GPT-5.2 support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
GPT-5.4
GPT-5.2
License
Usage and distribution terms
Both models are licensed under proprietary licenses.
Both models have usage restrictions defined by their respective organizations.
Proprietary
Closed source
Proprietary
Closed source
Release Timeline
When each model was launched
GPT-5.4 was released on 2026-03-05, while GPT-5.2 was released on 2025-12-11.
GPT-5.4 is 3 months newer than GPT-5.2.
Mar 5, 2026
1 weeks ago
2mo newerDec 11, 2025
3 months ago
Knowledge Cutoff
When training data ends
GPT-5.2 has a documented knowledge cutoff of 2025-08-25, while GPT-5.4's cutoff date is not specified.
We can confirm GPT-5.2's training data extends to 2025-08-25, but cannot make a direct comparison without GPT-5.4's cutoff date.
—
Aug 2025
Provider Availability
GPT-5.4 is available from OpenAI. GPT-5.2 is available from OpenAI. The availability of providers can affect quality of the model and reliability.
GPT-5.4
GPT-5.2
Outputs Comparison
Key Takeaways
GPT-5.4
View detailsOpenAI
GPT-5.2
View detailsOpenAI