OpenAI model product
GPT-4.5
5 is an OpenAI large language model for reasoning, coding, and creative tasks.
Updated Oct 23, 2026. Default version: GPT-4.5
LLMBoard Score34.2GPT-4.5
Coverage80%26 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkInternal API instruction following (hard) | Score54.00% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Lancer | Score37.30% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkComplexFuncBench | Score63.00% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score97.00% | Rank04 | Participants48 | Percentile93.62% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score90.80% | Rank04 | Participants103 | Percentile97.06% | EvidenceC | Evaluated |
| BenchmarkSWE-Lancer (IC-Diamond subset) | Score17.40% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score72.60% | Rank05 | Participants12 | Percentile63.64% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score90.00% | Rank06 | Participants18 | Percentile70.59% | EvidenceC | Evaluated |
| BenchmarkCOLLIE | Score72.30% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkOpenAI-MRCR: 2 needle 128k | Score38.50% | Rank06 | Participants9 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot Edit | Score44.90% | Rank07 | Participants10 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS <128k | Score72.30% | Rank07 | Participants13 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score62.50% | Rank08 | Participants47 | Percentile84.78% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score72.30% | Rank11 | Participants40 | Percentile74.36% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score50.00% | Rank11 | Participants23 | Percentile54.55% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score68.40% | Rank13 | Participants25 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score70.80% | Rank19 | Participants25 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score75.20% | Rank23 | Participants66 | Percentile66.15% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score43.80% | Rank25 | Participants34 | Percentile27.27% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.00% | Rank27 | Participants66 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score88.20% | Rank28 | Participants70 | Percentile60.87% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score85.10% | Rank33 | Participants51 | Percentile36.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score36.70% | Rank52 | Participants54 | Percentile3.77% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score55.40% | Rank53 | Participants60 | Percentile11.86% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,224.99 rating | Rank61 | Participants113 | Percentile46.43% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,444.69 rating | Rank64 | Participants218 | Percentile70.97% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,194.89 rating | Rank77 | Participants113 | Percentile32.14% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,417.40 rating | Rank94 | Participants218 | Percentile57.14% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score38.00% | Rank113 | Participants120 | Percentile5.88% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score69.50% | Rank151 | Participants256 | Percentile41.18% | EvidenceC | Evaluated |
GPT-4.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categorygerman | Rank25 | Rating / score1,477.24 | Votes319 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank36 | Rating / score1,456.68 | Votes319 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank36 | Rating / score1,439.47 | Votes271 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank42 | Rating / score1,435.40 | Votes2,627 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank42 | Rating / score1,447.48 | Votes4,092 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank43 | Rating / score1,415.91 | Votes271 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank45 | Rating / score1,436.30 | Votes2,618 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank46 | Rating / score1,468.64 | Votes701 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank47 | Rating / score1,466.03 | Votes2,052 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank53 | Rating / score1,413.84 | Votes215 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank56 | Rating / score1,438.48 | Votes6,122 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank57 | Rating / score1,452.19 | Votes10,031 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank59 | Rating / score1,447.51 | Votes1,430 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank61 | Rating / score1,444.03 | Votes2,052 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank61 | Rating / score1,224.99 | Votes2,925 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank62 | Rating / score1,436.60 | Votes5,501 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank63 | Rating / score1,391.88 | Votes215 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank64 | Rating / score1,444.69 | Votes14,547 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank65 | Rating / score1,411.66 | Votes4,092 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank65 | Rating / score1,218.76 | Votes1,392 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank71 | Rating / score1,206.22 | Votes77 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank75 | Rating / score1,443.26 | Votes1,796 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank75 | Rating / score1,175.99 | Votes77 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank76 | Rating / score1,399.24 | Votes2,627 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank76 | Rating / score1,447.10 | Votes8,425 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank77 | Rating / score1,418.95 | Votes1,430 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank77 | Rating / score1,194.89 | Votes2,925 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank78 | Rating / score1,433.45 | Votes701 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank78 | Rating / score1,412.93 | Votes6,122 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank78 | Rating / score1,190.72 | Votes1,392 | ObservationsN/A | Result date |
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 Runtime Performance
Provider-specific output speed and catalog latency for GPT-4.5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed50.00 tok/s | Catalog Latency20.00 s | Max Input128K | Max Output4.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
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 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGPT-4.5 | Released | LLMBoard34.20 | ParametersN/A | Context128K | Max output4.1K | Open weightsNo | LicenseProprietary |
Models similar to GPT-4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
o1
OpenAI
OP
o3 mini
OpenAI
OP
o1 pro
OpenAI
OP
GPT-4.1
OpenAI
OP
GPT-5-Nano
OpenAI
OP
GPT-5.3
OpenAI
What is GPT-4.5?
Key information about GPT-4.5 and its available data.
5 is an OpenAI large language model with improved reasoning, coding, creative capabilities, instruction following, and factual accuracy compared with GPT-4. It also provides faster performance, longer context handling, and reduced hallucinations.
Data as of 2026-10-22.
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.