OpenAI model product
GPT-4.5
5 is OpenAI's most advanced model, offering improved reasoning, coding, and creative capabilities with faster performance and longer context handling than GPT-4.
Updated Aug 12, 2026. Default version: GPT-4.5
LLMBoard score36.2GPT-4.5
Coverage100%26 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
GPT-4.5 Specifications
Technical details for the model's default version.
- Version
- GPT-4.5
- Released
- Feb 27, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 128K
- Max output
- 4.1K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-4.5 Benchmark Results
Benchmark scores for GPT-4.5.
| Internal API instruction following (hard) | 54.0% | 02 | 7 | 83.3% | C | |
| SWE-Lancer | 37.3% | 02 | 4 | 66.7% | C | |
| MMLU | 90.8% | 03 | 100 | 98.0% | C | |
| ComplexFuncBench | 63.0% | 04 | 7 | 50.0% | C | |
| Graphwalks parents <128k | 72.6% | 04 | 11 | 70.0% | C | |
| GSM8k | 97.0% | 04 | 48 | 93.6% | C | |
| SWE-Lancer (IC-Diamond subset) | 17.4% | 04 | 6 | 40.0% | C | |
| CharXiv-D | 90.0% | 05 | 16 | 73.3% | C | |
| COLLIE | 72.3% | 05 | 10 | 55.6% | C | |
| Graphwalks BFS <128k | 72.3% | 06 | 11 | 50.0% | C | |
| OpenAI-MRCR: 2 needle 128k | 38.5% | 06 | 9 | 37.5% | C | |
| Aider-Polyglot Edit | 44.9% | 07 | 10 | 33.3% | C | |
| SimpleQA | 62.5% | 08 | 46 | 84.4% | C | |
| MathVista | 72.3% | 10 | 39 | 76.3% | C | |
| TAU-bench Airline | 50.0% | 11 | 23 | 54.5% | C | |
| TAU-bench Retail | 68.4% | 13 | 25 | 50.0% | C | |
| Multi-IF | 70.8% | 16 | 20 | 21.1% | C | |
| MMMU | 75.2% | 20 | 63 | 69.3% | C | |
| Multi-Challenge | 43.8% | 20 | 29 | 32.1% | C | |
| IFEval | 88.2% | 26 | 65 | 60.9% | C | |
| HumanEval | 88.0% | 27 | 66 | 60.0% | C | |
| MMMLU | 85.1% | 33 | 49 | 33.3% | C | |
| CharXiv-R | 55.4% | 41 | 48 | 14.9% | C | |
| AIME 2024 | 36.7% | 51 | 53 | 3.9% | C | |
| SWE-Bench Verified | 38.0% | 98 | 105 | 6.7% | C | |
| GPQA | 69.5% | 132 | 234 | 43.8% | C |
GPT-4.5 Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 56 | 1226.0 | 2,925 | N/A | |
| text style control | overall | 69 | 1444.7 | 14,547 | N/A | |
| vision | overall | 75 | 1195.1 | 2,925 | N/A | |
| text | overall | 105 | 1417.4 | 14,547 | N/A |
GPT-4.5 Runtime Performance
Provider-specific output speed and catalog latency for GPT-4.5. Runtime does not affect the capability score.
| OpenAI | 50 tok/s | 20 s | 128K | 4.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-4.5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-4.5 | 36.2 | N/A | 128K | 4.1K | No | Proprietary |
What is GPT-4.5?
Key information about GPT-4.5 and its available data.
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.
Data as of 2026-08-11.
GPT-4.5 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
o3 mini
OpenAI
OP
o1
OpenAI
OP
o1 pro
OpenAI
OP
GPT-4.1
OpenAI
OP
GPT-5-nano
OpenAI
OP
GPT-5.3
OpenAI
FAQ
Common questions about GPT-4.5.
When was GPT-4.5 released?
GPT-4.5's default version was released on Feb 27, 2025.
How much does GPT-4.5 cost?
No official standard PAYG price is currently available for GPT-4.5.
Who created GPT-4.5?
GPT-4.5 was created by OpenAI.
What is the context window for GPT-4.5?
The default version has a 128K token context window.
Is GPT-4.5 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-4.5?
No provider offering is currently linked to the default version.
What models should I compare GPT-4.5 with?
Nearby ranked alternatives include Qwen3 Next 80B A3B, o1, o3 mini.