OpenAI model product
GPT-5-Codex
GPT-5-Codex is an OpenAI large language model trained for code review and identifying potential security vulnerabilities, performance issues, and bugs.
Updated Oct 23, 2026. Default version: GPT-5 Codex
LLMBoard Score43.8GPT-5 Codex
Coverage60%1 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
GPT-5-Codex Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5-Codex Benchmark Results
Benchmark scores for GPT-5 Codex.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA AIME 2025 | Score98.67% | Rank01 | Participants96 | Percentile100.00% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score74.15% | Rank25 | Participants168 | Percentile85.63% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score38.70% | Rank40 | Participants201 | Percentile80.50% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Verified | Score74.50% | Rank44 | Participants120 | Percentile63.87% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score5.14% | Rank50 | Participants200 | Percentile75.38% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score27.85% | Rank62 | Participants200 | Percentile69.35% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score83.74% | Rank81 | Participants199 | Percentile59.60% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score71.67% | Rank83 | Participants193 | Percentile57.29% | EvidenceB | EvaluatedN/A |
GPT-5-Codex Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
GPT-5-Codex Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $1.1 input, $9 output per 1M via Poe
- Tracked offerings
- 4
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/gpt-5-codex | Regionglobal | Input / 1M$1.1 | Output / 1M$9 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5-codex | Regionglobal | Input / 1M$1.25 | Output / 1M$10 | Context400K | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5-codex | Regionglobal | Input / 1M$1.25 | Output / 1M$10 | Context400K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5-codex | Regionglobal | Input / 1M$1.25 | Output / 1M$10 | Context400K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5-Codex Runtime Performance
Provider-specific output speed and catalog latency for GPT-5 Codex. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5-Codex Specifications
Technical details for the model's default version.
- Version
- GPT-5 Codex
- Released
- Sep 15, 2025
- Knowledge cutoff
- Sep 30, 2024
- Parameters
- N/A
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5-Codex 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-5 Codex | Released | LLMBoard43.84 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Models similar to GPT-5-Codex
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
o4 mini
OpenAI
OP
GPT-OSS-120B
OpenAI
OP
GPT-5-Mini
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-5.3
OpenAI
OP
GPT-5.4-nano
OpenAI
What is GPT-5-Codex?
Key information about GPT-5-Codex and its available data.
GPT-5-Codex is an OpenAI large language model designed for code reviews. It navigates codebases and analyzes code patterns to identify potential security vulnerabilities, performance issues, and bugs.
Data as of 2026-10-22.
FAQ
Common questions about GPT-5-Codex.
When was GPT-5-Codex released?
GPT-5-Codex's default version was released on Sep 15, 2025.
How much does GPT-5-Codex cost?
No official standard PAYG price is currently available for GPT-5-Codex. The lowest tracked third-party offer starts at $1.1 input and $9 output via Poe.
Who created GPT-5-Codex?
GPT-5-Codex was created by OpenAI.
What is the context window for GPT-5-Codex?
A context window is not available for the default version.
Is GPT-5-Codex open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5-Codex?
4 provider offerings are linked to the default version.