OpenAI model product
GPT-4-Turbo
GPT-4-Turbo is an OpenAI large language model with updated knowledge, improved performance, faster response times, and more affordable pricing than previous versions.
Updated Sep 8, 2026. Default version: GPT-4 Turbo
LLMBoard Score12.6GPT-4 Turbo
Coverage20%6 benchmark families
Context window128KTokens
Official input price$10OpenAI API
GPT-4-Turbo Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-4-Turbo Benchmark Results
Benchmark scores for GPT-4 Turbo.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkDROP | Score86.00% | Rank05 | Participants30 | Percentile86.21% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score88.50% | Rank11 | Participants31 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score86.50% | Rank29 | Participants101 | Percentile72.00% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score87.10% | Rank30 | Participants66 | Percentile55.38% | EvidenceC | Evaluated |
| BenchmarkMATH | Score72.60% | Rank33 | Participants71 | Percentile54.29% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,089.86 rating | Rank91 | Participants107 | Percentile15.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,112.18 rating | Rank92 | Participants107 | Percentile14.15% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,324.05 rating | Rank164 | Participants210 | Percentile22.01% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,271.47 rating | Rank179 | Participants210 | Percentile14.83% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score48.00% | Rank197 | Participants247 | Percentile20.33% | EvidenceC | Evaluated |
GPT-4-Turbo Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorychinese | Rank83 | Rating / score1,044.18 | Votes937 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank86 | Rating / score1,063.27 | Votes937 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank91 | Rating / score1,089.86 | Votes13,391 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank92 | Rating / score1,096.33 | Votes8,417 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank92 | Rating / score1,112.18 | Votes13,391 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank93 | Rating / score1,112.10 | Votes8,417 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank117 | Rating / score1,363.32 | Votes178 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank131 | Rating / score1,301.75 | Votes178 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank140 | Rating / score1,322.54 | Votes14,396 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank140 | Rating / score1,250.77 | Votes2,112 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank141 | Rating / score1,263.28 | Votes2,668 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank143 | Rating / score1,311.45 | Votes3,359 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank143 | Rating / score1,329.44 | Votes24,529 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank145 | Rating / score1,193.88 | Votes2,112 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank146 | Rating / score1,313.57 | Votes14,793 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank148 | Rating / score1,314.04 | Votes1,430 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank149 | Rating / score1,259.18 | Votes3,359 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank149 | Rating / score1,335.34 | Votes1,402 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank152 | Rating / score1,186.39 | Votes2,668 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank153 | Rating / score1,275.22 | Votes1,402 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank158 | Rating / score1,259.18 | Votes1,430 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank162 | Rating / score1,296.27 | Votes13,217 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank163 | Rating / score1,312.75 | Votes9,938 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank164 | Rating / score1,258.06 | Votes14,793 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank164 | Rating / score1,324.05 | Votes98,114 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank165 | Rating / score1,268.30 | Votes14,396 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank165 | Rating / score1,271.59 | Votes13,217 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank165 | Rating / score1,336.29 | Votes5,381 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank166 | Rating / score1,340.99 | Votes55,116 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank167 | Rating / score1,317.00 | Votes10,827 | ObservationsN/A | Result date |
GPT-4-Turbo Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $10 input, $30 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-turbo | Regionglobal | Input / 1M$10 | Output / 1M$30 | 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-4-Turbo Runtime Performance
Provider-specific output speed and catalog latency for GPT-4 Turbo. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed100.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output4.1K | Updated |
| ProviderAzure | Output Speed97.00 tok/s | Catalog Latency0.60 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-Turbo Specifications
Technical details for the model's default version.
- Version
- GPT-4 Turbo
- Released
- Apr 9, 2024
- Knowledge cutoff
- Dec 31, 2023
- Parameters
- N/A
- Context window
- 128K
- Max output
- 4.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-4-Turbo 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 Turbo | Released | LLMBoard12.63 | ParametersN/A | Context128K | Max output4.1K | Open weightsNo | LicenseProprietary |
Models similar to GPT-4-Turbo
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
o1 mini
OpenAI
OP
GPT-4o-mini
OpenAI
OP
GPT-4
OpenAI
OP
GPT-4o
OpenAI
OP
GPT-4.1-nano
OpenAI
OP
GPT-4.1-mini
OpenAI
What is GPT-4-Turbo?
Key information about GPT-4-Turbo and its available data.
GPT-4-Turbo is a GPT-4 model from OpenAI. It is described as having updated knowledge, improved performance, enhanced capabilities, faster response times, and more affordable pricing than previous versions.
Data as of 2026-09-08.
FAQ
Common questions about GPT-4-Turbo.
When was GPT-4-Turbo released?
GPT-4-Turbo's default version was released on Apr 9, 2024.
How much does GPT-4-Turbo cost?
GPT-4-Turbo's official API price is $10 per million input tokens and $30 per million output tokens via OpenAI.
Who created GPT-4-Turbo?
GPT-4-Turbo was created by OpenAI.
What is the context window for GPT-4-Turbo?
The default version has a 128K token context window.
Is GPT-4-Turbo open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-4-Turbo?
1 provider offerings are linked to the default version.