OpenAI model product
GPT-4o
GPT-4o is a multimodal AI model from OpenAI that accepts text, audio, image, and video inputs and generates text, audio, and image outputs.
Updated Sep 8, 2026. Default version: GPT-4o
LLMBoard Score22.6GPT-4o
Coverage60%37 benchmark families
Context window128KTokens
Official input price$2.5OpenAI API
GPT-4o Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-4o Benchmark Results
Benchmark scores for GPT-4o.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkActivityNet | Score61.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkComplexFuncBench | Score66.50% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score94.20% | Rank03 | Participants34 | Percentile93.94% | EvidenceC | Evaluated |
| BenchmarkEgoSchema | Score72.20% | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Lancer | Score32.60% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Lancer (IC-Diamond subset) | Score12.40% | Rank05 | Participants6 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkInternal API instruction following (hard) | Score29.20% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCOLLIE | Score61.00% | Rank08 | Participants10 | Percentile22.22% | EvidenceC | Evaluated |
| BenchmarkOpenAI-MRCR: 2 needle 128k | Score31.90% | Rank08 | Participants9 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot Edit | Score18.20% | Rank09 | Participants10 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS <128k | Score41.70% | Rank10 | Participants11 | Percentile10.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score35.40% | Rank10 | Participants11 | Percentile10.00% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score85.70% | Rank12 | Participants26 | Percentile56.00% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score85.30% | Rank12 | Participants17 | Percentile31.25% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score92.80% | Rank15 | Participants28 | Percentile48.15% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score42.80% | Rank19 | Participants23 | Percentile18.18% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score30.70% | Rank20 | Participants22 | Percentile9.52% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score60.90% | Rank20 | Participants23 | Percentile13.64% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score60.30% | Rank20 | Participants25 | Percentile20.83% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score38.20% | Rank21 | Participants47 | Percentile56.52% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score40.30% | Rank22 | Participants29 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score45.50% | Rank22 | Participants24 | Percentile8.70% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score63.40% | Rank24 | Participants27 | Percentile11.54% | EvidenceC | Evaluated |
| BenchmarkVideoMMMU | Score61.20% | Rank25 | Participants26 | Percentile4.00% | EvidenceC | Evaluated |
| BenchmarkERQA | Score35.20% | Rank26 | Participants26 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score61.40% | Rank26 | Participants39 | Percentile34.21% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score72.20% | Rank29 | Participants64 | Percentile55.56% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score23.50% | Rank35 | Participants36 | Percentile2.86% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score85.70% | Rank37 | Participants101 | Percentile64.00% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score81.40% | Rank38 | Participants49 | Percentile22.92% | EvidenceC | Evaluated |
GPT-4o Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorychinese | Rank85 | Rating / score1,071.23 | Votes186 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank86 | Rating / score1,008.38 | Votes186 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank90 | Rating / score1,119.07 | Votes3,376 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank91 | Rating / score1,121.07 | Votes1,744 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank94 | Rating / score1,064.54 | Votes3,376 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank95 | Rating / score1,071.66 | Votes1,744 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank121 | Rating / score1,291.91 | Votes1,104 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank126 | Rating / score1,288.81 | Votes712 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank133 | Rating / score1,234.19 | Votes1,104 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank136 | Rating / score1,326.46 | Votes6,756 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank137 | Rating / score1,340.43 | Votes12,147 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank138 | Rating / score1,324.40 | Votes7,043 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank139 | Rating / score1,217.94 | Votes712 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank140 | Rating / score1,312.93 | Votes1,202 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank144 | Rating / score1,327.85 | Votes546 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank150 | Rating / score1,327.69 | Votes457 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank152 | Rating / score1,257.05 | Votes1,202 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank153 | Rating / score1,268.10 | Votes546 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank154 | Rating / score1,347.83 | Votes2,674 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank154 | Rating / score1,338.44 | Votes6,160 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank155 | Rating / score1,324.03 | Votes5,517 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank156 | Rating / score1,316.15 | Votes20,213 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank157 | Rating / score1,312.81 | Votes5,805 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank157 | Rating / score1,326.90 | Votes8,201 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank158 | Rating / score1,262.45 | Votes457 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank158 | Rating / score1,285.33 | Votes6,826 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank158 | Rating / score1,308.52 | Votes6,826 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank159 | Rating / score1,289.29 | Votes12,147 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank160 | Rating / score1,274.39 | Votes6,756 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank160 | Rating / score1,330.47 | Votes3,778 | ObservationsN/A | Result date |
GPT-4o Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2.5 input, $10 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $2.5 input, $10 output per 1M via OrcaRouter
- Tracked offerings
- 7
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOrcaRouter | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderOpenAI | Provider model IDgpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-4o-2024-08-06 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-4o Runtime Performance
Provider-specific output speed and catalog latency for GPT-4o. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed132.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output16.4K | Updated |
| ProviderAzure | Output Speed99.00 tok/s | Catalog Latency0.53 s | Max Input128K | Max Output16.4K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-4o Specifications
Technical details for the model's default version.
- Version
- GPT-4o
- Released
- Aug 6, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 128K
- Max output
- 16.4K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-4o 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-4o | Released | LLMBoard22.64 | ParametersN/A | Context128K | Max output16.4K | Open weightsNo | LicenseProprietary |
| VersionChatGPT-4o Latest | Released | LLMBoardN/A | ParametersN/A | Context128K | Max output16.4K | Open weightsNo | LicenseProprietary |
| VersionGPT-4o | Released | LLMBoardN/A | ParametersN/A | Context128K | Max output4.1K | Open weightsNo | LicenseProprietary |
Models similar to GPT-4o
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-4.1-mini
OpenAI
OP
GPT-5-Nano
OpenAI
OP
o1 mini
OpenAI
OP
GPT-4.1
OpenAI
OP
GPT-4-Turbo
OpenAI
OP
o1 pro
OpenAI
What is GPT-4o?
Key information about GPT-4o and its available data.
GPT-4o, with “o” referring to “omni,” is OpenAI’s multimodal AI model. It matches GPT-4 Turbo performance on text and code and improves on non-English languages, vision, and audio understanding.
Data as of 2026-09-08.
FAQ
Common questions about GPT-4o.
When was GPT-4o released?
GPT-4o's default version was released on Aug 6, 2024.
How much does GPT-4o cost?
GPT-4o's official API price is $2.5 per million input tokens and $10 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $2.5 input and $10 output via OrcaRouter.
Who created GPT-4o?
GPT-4o was created by OpenAI.
What is the context window for GPT-4o?
The default version has a 128K token context window.
Is GPT-4o open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-4o?
7 provider offerings are linked to the default version.