GPT-5.4 (low)
OpenAIGPTProprietary
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
file, image, text
Capability Radar
44
general
46
coding
87
reasoning
63
scienceest.
70
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 18 | 68.0 | LS |
| Code Ranking | 27 | 79.0 | AA |
| General Ranking | 57 | 77.0 | AA |
| Multimodal Ranking | 10 | 89.0 | LS |
| Reasoning | 15 | 87.0 | LS |
| Science | 23 | 80.0 | AA |
Benchmark Scores (LLM Stats)
Agents
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
Biology
GPQA
92.8%SR
Communication
Tau2 Telecom
98.9%SR
General
MMMU-Pro
81.2%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
Intelligence Index47.9
Coding Index45.6
Gpqa0.9
Tau20.7
Lcr0.7
Ifbench0.7
Scicode0.5
Terminalbench Hard0.4
Hle0.3
LLM Stats Category Scores
Communication100
Structured Output90
Biology90
Chemistry90
Physics90
Vision80
General80
Multimodal80
Search80
Spatial Reasoning70
Tool Calling70
Agents70
Code70
Reasoning70
Finance60
Long Context40
Math40
Healthcare30
Pricing
Input Price$2.5 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$5.625 / 1M tokens
Speed
Tokens/sec67.1 tokens/s
Time to First Token1.85s
Time to Answer1.85s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| OpenAI | 2.5M | 15.0M |