GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Tested on 34 benchmarks · BenchGecko score 66.0. Top scores: Chatbot Arena Elo — Overall (1464.8%), Chatbot Arena Elo — Coding (1395.0%), OTIS Mock AIME 2024-2025 (97.8%).
Gemini 3.7 Flash scores 66.4 (101% as good) at $0.75/1M input · 70% cheaper
Complex terminal-based engineering tasks. Models must use command-line tools, navigate filesystems, and debug systems through shell interaction.
Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
- Typemultimodal
- Context1.1M tokens (~525 books)
- ReleasedMar 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.020
Frequently Asked Questions
Related Models
Grok 4.6 · xAIClaude Sonnet 5 · AnthropicGPT-5.5 · OpenAIGemini 3.7 Flash · Google DeepMindClaude Opus 4.7 · AnthropicKey facts · as of 2026-10-05
- GPT-5.4 by OpenAI. BenchGecko score 66.0, rank 54 of 312 scored models (normalized average of public benchmark scores).
- List price $2.50 input · $15.00 output per 1M tokens (as of 2026-10-05).
- Sold by 7 providers (as of 2026-10-05): OpenAI $1.25 in / $7.50 out · Azure $2.50 in / $15.00 out · OpenAI $2.50 in / $15.00 out · Amazon Bedrock $2.75 in / $16.50 out · Azure $2.75 in / $16.50 out · and 2 more. Every provider
How to cite · data as of 2026-10-05
GPT-5.4 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-5-4
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP