Inference
EN
OpenAI

GPT-5.3 Codex

GPT-5.3 Codex is a reasoning model from OpenAI. 18 benchmarks count toward its index, in 6 categories.

  • Closed weights
  • Reasoning
  • Input: text · image · file
  • Released 2026-02
RankedEnough results for an index.
IndexAll categories, out of 100.62.0±5.3Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.52/sMedian 67/s
First tokenSeconds to the first output token.2.8 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.75Median $0.60
Output / 1MUS dollars per 1M output tokens.$14.00Median $2.55
ContextMaximum tokens in one request.400KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-5.3-codex
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.175
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DigitalOceanCloud$1.75$14.00400K
OpenRouterRouter$1.75$14.00400K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.6 counted60.663 / 218
CodingCode writing and repair.6 counted61.860 / 209
ReasoningLogic problems and puzzles.2 counted67.037 / 227
MultimodalTasks with images and text.1 counted57.3—
KnowledgeFacts and expert knowledge.2 counted64.149 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted59.5—
MathMath problems.None counted——

Results

18 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Terminal-Bench 2.0 · BenchLMAgentic77.3%2 / 41
Artificial Analysis Long Context ReasoningReasoning83.3%13 / 217
Software Engineering Benchmark VerifiedCoding85.0%9 / 114
Terminal-Bench 2.0 · Vals AIAgentic64.0% ±5.16 / 66
LiveCodeBenchCoding87.3% ±1.016 / 142
Artificial Analysis GPQA DiamondKnowledge91.5%25 / 199
Artificial Analysis IFBenchInstruction75.4%23 / 146
Artificial Analysis Humanity's Last ExamKnowledge42.5%38 / 222
IOI v1Coding43.8% ±7.812 / 61
Critical Physics TasksReasoning16.9%43 / 214
Gert Labs Composite Game BenchmarkAgentic57.5%13 / 52
Artificial Analysis MMMU-ProMultimodal78.5%36 / 113
τ²-Bench Tool-Agent-User EvaluationAgentic86.0%54 / 149
SWE-benchCoding78.0% ±1.933 / 87
SWE-Bench verified · Epoch AICoding74.8% ±2.015 / 32
Vibe Code Bench v1.1Coding61.8% ±4.758 / 123
IOICoding53.8% ±6.322 / 45
SWE-bench ProCoding56.8%46 / 83
JobBenchAgentic33.7%23 / 36
OSWorld-VerifiedAgentic64.7%28 / 37
SWE-RebenchCoding58.2%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedEpoch AICC BYmodels.devMIT

History

5 releases
Index64.0 → 62.0
23 Oct 202612 Nov 2026
Output / 1M$14.00 → $14.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5.3 Codex cost?
$1.75 per 1M input tokens, $14.00 per 1M output tokens.
How good is GPT-5.3 Codex?
Its index is 62.0 out of 100. That is place 63 of 283 ranked models.
What is GPT-5.3 Codex best at?
Reasoning: 67.0 out of 100, place 37 of 227.
How fast is GPT-5.3 Codex?
52 output tokens per second, 2.8 s to the first token.
What is the context window of GPT-5.3 Codex?
400K tokens.
Is GPT-5.3 Codex open source?
No. Its weights are not published.
When was GPT-5.3 Codex released?
February 2026.

Badge

GPT-5.3 Codex on Inference360: place 63 of 283, index 62.0
HTML
<a href="https://inference360.ai/models/gpt-5-3-codex"><img src="https://inference360.ai/badges/gpt-5-3-codex.svg" alt="GPT-5.3 Codex on Inference360: place 63 of 283, index 62.0" height="20"></a>
Markdown
[![GPT-5.3 Codex on Inference360: place 63 of 283, index 62.0](https://inference360.ai/badges/gpt-5-3-codex.svg)](https://inference360.ai/models/gpt-5-3-codex)

Compare with

Claude Opus 4.762.0DeepSeek V4 Flash 073161.9Gemini 3.1 Pro62.3Gemini 3.1 Pro Preview61.5GPT-5.2-Codex59.9

Lower price

dots3-note Preview63.4 · FreeGLM-5.3-Flash63.1 · $0.078/1MLing 3.1 Flash67.2 · $0.135/1M

More from OpenAI

All models
GPT-5.3-Codex-SparkUnrankedGPT AudioUnrankedGPT Audio MiniUnrankedGPT Realtime 1.5UnrankedGPT-5.3 InstantUnranked