OpenAI model product
GPT-4
GPT-4 is a large multimodal model capable of processing both image and text inputs and generating human-like text outputs.
Updated Aug 17, 2026. Default version: GPT-4
LLMBoard Score3.5GPT-4
Coverage80%8 benchmark families
Context window8.2KTokens
Official input price$30OpenAI API
GPT-4 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-4 Benchmark Results
Benchmark scores for GPT-4.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAI2 Reasoning Challenge (ARC) | Score96.3% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkLSAT | Score88.0% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSAT Math | Score89.0% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkUniform Bar Exam | Score90.0% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score87.5% | Rank01 | Participants22 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score95.3% | Rank02 | Participants27 | Percentile96.2% | EvidenceC | Evaluated |
| BenchmarkDROP | Score80.9% | Rank11 | Participants30 | Percentile65.5% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score74.5% | Rank21 | Participants31 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score86.4% | Rank30 | Participants101 | Percentile71.0% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score67.0% | Rank59 | Participants66 | Percentile10.8% | EvidenceC | Evaluated |
| BenchmarkMATH | Score42.0% | Rank66 | Participants71 | Percentile7.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score35.7% | Rank219 | Participants239 | Percentile8.4% | EvidenceC | Evaluated |
GPT-4 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 | Categoryoverall | Rank247 | Rating / score1312.9 | Votes93,439 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank248 | Rating / score1312.5 | Votes100,105 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank259 | Rating / score1263.6 | Votes100,105 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank261 | Rating / score1262.3 | Votes93,439 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank269 | Rating / score1287.1 | Votes54,173 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank280 | Rating / score1275.5 | Votes88,723 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank290 | Rating / score1206.1 | Votes54,173 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank301 | Rating / score1186.1 | Votes88,723 | ObservationsN/A | Result date |
GPT-4 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $30 input, $60 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- N/A
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenAI | Provider model IDgpt-4 | Regionglobal | Input / 1M$30 | Output / 1M$60 | Context8.2K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-4 Runtime Performance
Provider-specific output speed and catalog latency for GPT-4. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAzure | Output Speed104 tok/s | Catalog Latency0.3 s | Max Input32.8K | Max Output32.8K | Updated |
| ProviderOpenAI | Output Speed100 tok/s | Catalog Latency0.5 s | Max Input32.8K | Max Output32.8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-4 Specifications
Technical details for the model's default version.
- Version
- GPT-4
- Released
- Jun 13, 2023
- Knowledge cutoff
- Dec 31, 2022
- Parameters
- N/A
- Context window
- 8.2K
- Max output
- 8.2K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-4 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 | Released | LLMBoard3.5 | ParametersN/A | Context8.2K | Max output8.2K | Open weightsNo | LicenseProprietary |
GPT-4 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-4
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-4.1-nano
OpenAI
OP
GPT-3.5-Turbo
OpenAI
OP
GPT-5.1-Codex-Mini
OpenAI
OP
GPT-4o-mini
OpenAI
OP
GPT-4-Turbo
OpenAI
OP
o1 mini
OpenAI
What is GPT-4?
Key information about GPT-4 and its available data.
GPT-4 is a large multimodal model capable of processing both image and text inputs and generating human-like text outputs. It demonstrates human-level performance on various professional and academic benchmarks.
Data as of 2026-08-17.
FAQ
Common questions about GPT-4.
When was GPT-4 released?
GPT-4's default version was released on Jun 13, 2023.
How much does GPT-4 cost?
GPT-4's official API price is $30 per million input tokens and $60 per million output tokens via OpenAI.
Who created GPT-4?
GPT-4 was created by OpenAI.
What is the context window for GPT-4?
The default version has a 8.2K token context window.
Is GPT-4 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-4?
1 provider offerings are linked to the default version.
What models should I compare GPT-4 with?
Nearby ranked alternatives include Qwen2.5 Coder 32B, Phi 3.5 MoE, Nova Micro.