GPT-4.5 (Preview)
OpenAIGPTProprietary
Description
GPT-4.5 is OpenAI's most advanced model, offering improved reasoning, coding, and creative capabilities with faster performance and longer context handling than GPT-4. It features enhanced instruction following, reduced hallucinations, and better factual accuracy.
Release Date
2025-02-27
Parameters
—
Context Length
—
Modalities
image, text
Capability Radar
14
general
50
coding
80
reasoning
60
scienceest.
60
agents
70
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| General Ranking | 444 | 21.0 | AA |
| Multimodal Ranking | 52 | 75.0 | LS |
| Reasoning | 43 | 73.0 | LS |
Benchmark Scores (LLM Stats)
Biology
GPQA
69.5%SR
Code
HumanEval
88.0%SR
Aider-Polyglot Edit
44.9%SR
SWE-Bench Verified
38.0%SR
SWE-Lancer
37.3%SR
SWE-Lancer (IC-Diamond subset)
17.4%SR
Communication
Multi-IF
70.8%SR
TAU-bench Retail
68.4%SR
TAU-bench Airline
50.0%SR
Multi-Challenge
43.8%SR
Factuality
SimpleQA
62.5%SR
Finance
MMLU
90.8%SR
General
IFEval
88.2%SR
MMMLU
85.1%SR
MMMU
75.2%SR
Internal API instruction following (hard)
54.0%SR
Language
COLLIE
72.3%SR
Long Context
ComplexFuncBench
63.0%SR
OpenAI-MRCR: 2 needle 128k
38.5%SR
Math
GSM8k
97.0%SR
MathVista
72.3%SR
AIME 2024
36.7%SR
Multimodal
CharXiv-D
90.0%SR
CharXiv-R
55.4%SR
Reasoning
Graphwalks parents <128k
72.6%SR
Graphwalks BFS <128k
72.3%SR
AA Evaluation Indices
Intelligence Index13.6
LLM Stats Category Scores
Legal90
Finance90
Instruction Following80
Language80
Math80
Healthcare80
Multimodal70
Physics70
Spatial Reasoning70
Structured Output70
General70
Biology70
Chemistry70
Vision70
Writing70
Reasoning60
Factuality60
Communication60
Tool Calling60
Long Context50
Code50
Frontend Development40
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
No provider data available