GPT-5.4 (xhigh)
OpenAIGPT
Description
GPT-5.4 is OpenAI's most capable and efficient frontier model for professional work. It combines industry-leading coding capabilities with native computer-use, up to 1M tokens of context, full-resolution vision processing, tool search for large tool ecosystems, and improved reasoning across spreadsheets, presentations, and documents. It is the most token-efficient reasoning model in the GPT-5 series.
Release Date
2026-03-05
Parameters
—
Context Length
1.1M
Modalities
image, pdf, text
Capability Radar
49
general
69
coding
92
reasoning
70
scienceest.
70
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 43 | 58.0 | LS |
| Code Ranking | 6 | 94.0 | AA |
| General Ranking | 7 | 87.0 | AA |
| Multimodal Ranking | 12 | 89.0 | LS |
| Reasoning | 15 | 87.0 | LS |
| Science | 6 | 90.0 | AA |
Benchmark Scores (LLM Stats)
Agents
GDPval-AA
1429.00 / 3000SR
BrowseComp
82.7%SR
Terminal-Bench 2.0
75.1%SR
OSWorld-Verified
75.0%SR
MCP Atlas
67.2%SR
SWE-Bench Pro
57.7%SR
Finance Agent
56.0%SR
Toolathlon
54.6%SR
FrontierSWE
54.0%SR
Legal Agent Benchmark
0.4%SR
Biology
GPQA
92.8%SR
Communication
Tau2 Telecom
98.9%SR
General
MMMU-Pro
81.2%SR
LiveBench
80.3%SR
Long Context
Graphwalks parents >128k
32.4%SR
Graphwalks BFS >128k
21.4%SR
Math
FrontierMath
47.6%SR
Humanity's Last Exam
39.8%SR
Multimodal
OmniDocBench 1.5
89.1%SR
Reasoning
ARC-AGI
93.7%SR
Graphwalks BFS <128k
93.0%SR
Graphwalks parents <128k
89.8%SR
ARC-AGI v2
73.3%SR
AA Evaluation Indices
Coding Index71.1
Intelligence Index51.4
Gpqa0.9
Tau20.9
Terminalbench V2 10.8
Lcr0.7
Ifbench0.7
Terminalbench Hard0.6
Scicode0.6
Hle0.4
Tau Banking0.3
LLM Stats Category Scores
Finance100
Legal100
General100
Agents100
Reasoning63
Communication100
Physics90
Structured Output90
Biology90
Chemistry90
Multimodal80
Search80
Vision80
Spatial Reasoning70
Tool Calling70
Math60
Code60
Long Context40
Healthcare30
Pricing
Input Price$2.5 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$5.625 / 1M tokens
Cache Read Price$0.25 / 1M tokens
Speed
Tokens/sec169.1
Time to First Token111.73s
Time to Answer111.73s
Provider Price Ranking
Provider Price Ranking
13 providers
Cheapest: OpenAIMost Expensive: Cortecs
ProviderInputOutput
1OpenAIPRIMARY
$2.5
$15
2302.AI
$2.5
$15
3Abacus
$2.5
$15
4Vivgrid
$2.5
$15
5SAP AI Core
$2.5
$15
6GitHub Copilot
$2.5
$15
7OpenCode Zen
$2.5
$15
8AIHubMix
$2.5
$15
9Azure Cognitive Services
$2.5
$15
10LLM Gateway
$2.5
$15
11Azure
$2.5
$15
12FreeModel
$2.5
$15
13Cortecs
$3
$16.13
Compare pricing across different API providers for this model.