OpenAI model product
GPT-5 Medium is an OpenAI language model variant designed for moderately complex coding and agentic tasks with medium-effort reasoning.
Updated Sep 8, 2026. Default version: GPT-5 Medium
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for GPT-5 Medium.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGPQA | Score88.10% | Rank42 | Participants247 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score88.90% | Rank53 | Participants119 | Percentile55.93% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,418.97 rating | Rank54 | Participants97 | Percentile44.79% | EvidenceA | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categorywebdev-html | Rank51 | Rating / score1,428.64 | Votes3,034 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank54 | Rating / score1,418.97 | Votes3,034 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank54 | Rating / score1,418.97 | Votes3,034 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
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.
Provider-specific output speed and catalog latency for GPT-5 Medium. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed90.00 tok/s | Catalog Latency2.50 s | Max Input400K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGPT-5 | Released | LLMBoardN/A | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
| VersionGPT-5 High | Released | LLMBoardN/A | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
| VersionGPT-5 Medium | Released | LLMBoard48.83 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about GPT-5 and its available data.
GPT-5 Medium is an OpenAI large language model variant that provides medium-effort reasoning for moderately complex tasks. It is described as optimized for coding and agentic tasks, with more thorough analysis than instant responses and faster performance than high-effort reasoning.
Data as of 2026-09-08.
Common questions about GPT-5.
GPT-5's default version was released on Aug 7, 2025.
No official standard PAYG price is currently available for GPT-5.
GPT-5 was created by OpenAI.
The default version has a 400K token context window.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.