Coding-optimized GPT model for repository edits, reviews, and agentic software work
- Context
- 400K
- Released
- 8mo ago
- Input / 1M tokens
- $1.75
- Output / 1M tokens
- $14.00
- Cached input / 1M tokens
- $0.18
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
Other published benchmarks
| Evaluation | Reported score and source |
|---|---|
| SWE-Bench verified | |
| Terminal Bench | 70.3% Third-party evaluator · gpt-5.3-codex Agent: CodeBrain-1 External evaluation via Epoch AIOriginal-source terms apply |
| Terminal Bench | 75.8% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: CodeBrain-1.5 https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 75.7% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: Codelia https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 77.3% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: Droid https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 69.1% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: IndusAGI Coding Agent https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 74.6% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: Mux https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 78.4% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: SageAgent https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 75.1% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: Simple Codex https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 64.7% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: Terminus 2 https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
| Terminal Bench | 71.5% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · gpt-5.3-codex Agent: spoox-o-m https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply |
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Specifications
- Developer
- OpenAI
- Model family
- GPT
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- February 5, 2026
- Model ID
openai/gpt-5.3-codex- Openness
- Closed
- License
- —
- Input modalities
- text, image, file
- Output modalities
- text
- Modality
- text+image+file->text
- Tokenizer
- GPT
- Max output tokens
- 128K
- Knowledge cutoff
- 2025-08-31
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- openai/gpt-5.3-codex
- Source family
- gpt-codex
- Last updated
- 2026-02-05
- Knowledge cutoff
- 2025-08-31
- Model context
- 400K
- Maximum input
- 272K
- Model output limit
- 128K
- Open weights
- No
- File attachments
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Temperature control
- Yes
Published benchmarks
Complete source record (JSON)
{
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"family": "gpt-codex",
"last_updated": "2026-02-05",
"knowledge": "2025-08-31",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"benchmarks": [
{
"name": "SWE-Atlas Codebase QnA",
"score": 32.6,
"source": "https://labs.scale.com/leaderboard/sweatlas-qna",
"metric": "score",
"harness": "Codex"
},
{
"name": "SWE-Atlas Refactoring",
"score": 42.38,
"source": "https://labs.scale.com/leaderboard/sweatlas-refactoring",
"metric": "score",
"harness": "Codex"
},
{
"name": "SWE-Atlas Test Writing",
"score": 38.98,
"source": "https://labs.scale.com/leaderboard/sweatlas-tw",
"metric": "score",
"harness": "Codex"
}
],
"release_date": "2026-02-05",
"open_weights": false
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| azure | 400K | $1.75 | $14.00 | $0.18 | — | 96.30% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| openai | 400K | $1.75 | $14.00 | $0.18 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| openai/fast | 400K | $3.50 | $28.00 | $0.35 | — | — | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Text provenance
EU · product-scopedOpenAI textGrain watermarking
In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.
Official explanation