OpenAI model product
GPT-5.2-Codex
2-Codex is an OpenAI language model optimized for agentic coding tasks in Codex or similar environments.
Updated Oct 23, 2026. Default version: GPT-5.2 Codex
LLMBoard Score56.9GPT-5.2 Codex
Coverage60%3 benchmark families
Context window400KTokens
Official input priceN/AOfficial price unavailable
GPT-5.2-Codex Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.2-Codex Benchmark Results
Benchmark scores for GPT-5.2 Codex.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA IFBench | Score77.62% | Rank09 | Participants168 | Percentile95.21% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score82.33% | Rank14 | Participants193 | Percentile93.23% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench | Score74.30% | Rank17 | Participants38 | Percentile56.76% | EvidenceB | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score64.00% | Rank18 | Participants53 | Percentile67.31% | EvidenceC | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score88.77 score | Rank21 | Participants43 | Percentile52.38% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench instruction (2026-06-25) | Score66.45 score | Rank29 | Participants43 | Percentile33.33% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score41.07% | Rank32 | Participants201 | Percentile84.50% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench reasoning (2026-06-25) | Score77.71 score | Rank35 | Participants43 | Percentile19.05% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score89.90% | Rank36 | Participants199 | Percentile82.32% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Pro | Score56.40% | Rank38 | Participants63 | Percentile40.32% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score8.67% | Rank39 | Participants200 | Percentile80.90% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score35.73% | Rank39 | Participants200 | Percentile80.90% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,338.80 rating | Rank88 | Participants107 | Percentile17.92% | EvidenceA | Evaluated |
GPT-5.2-Codex Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categorywebdev-react | Rank83 | Rating / score1,329.34 | Votes4,355 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank88 | Rating / score1,338.80 | Votes6,718 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank88 | Rating / score1,338.80 | Votes6,718 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank88 | Rating / score1,348.39 | Votes2,359 | ObservationsN/A | Result date |
GPT-5.2-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 $0.14 input, $1.14 output per 1M via QiHang
- Tracked offerings
- 18
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderQiHang | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$0.14 | Output / 1M$1.14 | Context400K | Updated |
| ProviderPoe | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.6 | Output / 1M$13 | Context400K | Updated |
| ProviderOrcaRouter | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderJiekou.AI | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderVivgrid | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderAzure Cognitive Services | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderOpenCode | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderAzure | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderAIHubMix | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
| ProviderAbacus | Provider model IDgpt-5.2-codex | Regionglobal | Input / 1M$1.75 | Output / 1M$14 | Context400K | Updated |
GPT-5.2-Codex Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.2 Codex. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed50.00 tok/s | Catalog Latency3.00 s | Max Input400K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5.2-Codex Specifications
Technical details for the model's default version.
- Version
- GPT-5.2 Codex
- Released
- Jan 14, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.2-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-5.2 Codex | Released | LLMBoard56.85 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5.2-Codex
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.4-mini
OpenAI
OP
GPT-5.1
OpenAI
OP
GPT-5.1-Instant
OpenAI
OP
GPT-5.3-Codex
OpenAI
OP
GPT-5.5-Instant
OpenAI
OP
o3
OpenAI
What is GPT-5.2-Codex?
Key information about GPT-5.2-Codex and its available data.
2 with higher reasoning capabilities for agentic coding tasks. It is available in the Responses API, and its underlying model snapshot is regularly updated.
Data as of 2026-10-22.
FAQ
Common questions about GPT-5.2-Codex.
When was GPT-5.2-Codex released?
GPT-5.2-Codex's default version was released on Jan 14, 2026.
How much does GPT-5.2-Codex cost?
No official standard PAYG price is currently available for GPT-5.2-Codex. The lowest tracked third-party offer starts at $0.14 input and $1.14 output via QiHang.
Who created GPT-5.2-Codex?
GPT-5.2-Codex was created by OpenAI.
What is the context window for GPT-5.2-Codex?
The default version has a 400K token context window.
Is GPT-5.2-Codex open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.2-Codex?
18 provider offerings are linked to the default version.