How accurate is GPT-5.3-Codex?

GPT-5.3-Codex answered 66 of 80 questions correctly (82.5%) in our 2026-10-27 run, ranking #3 of 78 models.

How fast is GPT-5.3-Codex?

GPT-5.3-Codex generated a median of 95 output tokens per second in our 2026-10-27 run, ranking #40 of 78. Median time to first token was 1.4 s.

What is the latency of GPT-5.3-Codex?

GPT-5.3-Codex had a median time to first token of 1.4 s in our 2026-10-27 run, ranking #57 of 78 models.

How much does GPT-5.3-Codex cost?

GPT-5.3-Codex cost $0.01 per question on average as billed in our 2026-10-27 run, reasoning tokens included.

What is GPT-5.3-Codex API pricing?

GPT-5.3-Codex is listed at $1.75 per million input tokens and $14 per million output tokens on OpenRouter.

What is the context window of GPT-5.3-Codex?

GPT-5.3-Codex accepts up to 400,000 tokens of context, according to OpenRouter's model catalogue.

Who makes GPT-5.3-Codex?

GPT-5.3-Codex is made by OpenAI. We tested it through OpenRouter using the model ID openai/gpt-5.3-codex.

Where can I use GPT-5.3-Codex via API?

Through OpenRouter, GPT-5.3-Codex is served by 1 host: OpenAI.

OpenAIReleased 24 Feb 2026

GPT-5.3-Codex benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 27 Oct 2026

Compare

Available through OpenRouter on

Azure$1.75 in · $14 out
OpenAI$1.75 in · $14 out

Intelligence82.5% correct#3 of 72

Speed95tok/s#40 of 72

Cost$0.01per question#59 of 72List $1.75 in · $14 out per 1M

Verbosity699tokens per question#24 of 72

Summary

Answers 66 of 80 verification questions correctly (82.5%), placing #3 of 72 models tested on the current suite.
Generates 95 output tokens per second, faster than 45% of the models we measure.
Starts responding after 1.4 s (median time to first token), including thinking time.
Costs $0.01 per question as billed, #18 cheapest of 31 models priced over $1 per 1M tokens.

Specifications

Reasoning: Yes
Input: text, image, file
Output: text
Context window: 400k tokens
Weights: —
Knowledge cutoff: —
OpenRouter ID: openai/gpt-5.3-codex
Last tested: 27 Oct 2026

Peer group: 34 models with a blended list price over $1 per 1M tokens (3 input : 1 output). Charts below compare GPT-5.3-Codex with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

GPT-5.3-Codex circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

GPT-5.3-Codex circled · accurate and quick sits top left

Score vs. tokens per question

GPT-5.3-Codex circled · output tokens, reasoning included

Verification score

All models tested on the current suite

62 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price over $1

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
59GPT-5.3-Codex$0.01

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group (over $1) · higher is better

18 more models · see the full leaderboard

Time to first token

Peer group (over $1) · lower is better

20 more models · see the full leaderboard

End-to-end response time

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

Latency vs. output speed

GPT-5.3-Codex circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science28/30

Engineering11/15

Medicine7/11

Economics8/9

Law4/6

Humanities & social science8/9

More from OpenAI

OpenAI#12GPT-6 Astra76.2% verification score49 tok/s1.3 s first token$0.013 / question

OpenAI#12GPT-6.1 Terra Pro76.2% verification score— tok/s8.5 s first token$0.005 / question

OpenAI#12GPT-6.1 Sol76.2% verification score41 tok/s2.1 s first token$0.0029 / question

All OpenAI models →

Compare GPT-5.3-Codex

Head to head with its closest rivals, other OpenAI models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
Azure	$1.75	$14	400k	128k	—
OpenAI	$1.75	$14	400k	128k	—

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

GPT-5.3-Codex on OpenRouter: list prices and hosts
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

GPT-5.3-Codex: frequently asked questions

How accurate is GPT-5.3-Codex?: GPT-5.3-Codex answered 66 of 80 questions correctly (82.5%) in our 2026-10-27 run, ranking #3 of 78 models.
How fast is GPT-5.3-Codex?: GPT-5.3-Codex generated a median of 95 output tokens per second in our 2026-10-27 run, ranking #40 of 78. Median time to first token was 1.4 s.
What is the latency of GPT-5.3-Codex?: GPT-5.3-Codex had a median time to first token of 1.4 s in our 2026-10-27 run, ranking #57 of 78 models.
How much does GPT-5.3-Codex cost?: GPT-5.3-Codex cost $0.01 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is GPT-5.3-Codex API pricing?: GPT-5.3-Codex is listed at $1.75 per million input tokens and $14 per million output tokens on OpenRouter.
What is the context window of GPT-5.3-Codex?: GPT-5.3-Codex accepts up to 400,000 tokens of context, according to OpenRouter's model catalogue.
Who makes GPT-5.3-Codex?: GPT-5.3-Codex is made by OpenAI. We tested it through OpenRouter using the model ID openai/gpt-5.3-codex.
Where can I use GPT-5.3-Codex via API?: Through OpenRouter, GPT-5.3-Codex is served by 1 host: OpenAI.

OpenAIReleased 24 Feb 2026

GPT-5.3-Codex benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 27 Oct 2026

Compare

Available through OpenRouter on

Azure$1.75 in · $14 out
OpenAI$1.75 in · $14 out

Intelligence82.5% correct#3 of 72

Speed95tok/s#40 of 72

Cost$0.01per question#59 of 72List $1.75 in · $14 out per 1M

Verbosity699tokens per question#24 of 72

Summary

Answers 66 of 80 verification questions correctly (82.5%), placing #3 of 72 models tested on the current suite.
Generates 95 output tokens per second, faster than 45% of the models we measure.
Starts responding after 1.4 s (median time to first token), including thinking time.
Costs $0.01 per question as billed, #18 cheapest of 31 models priced over $1 per 1M tokens.

Specifications

Reasoning: Yes
Input: text, image, file
Output: text
Context window: 400k tokens
Weights: —
Knowledge cutoff: —
OpenRouter ID: openai/gpt-5.3-codex
Last tested: 27 Oct 2026

Peer group: 34 models with a blended list price over $1 per 1M tokens (3 input : 1 output). Charts below compare GPT-5.3-Codex with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

GPT-5.3-Codex circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

GPT-5.3-Codex circled · accurate and quick sits top left

Score vs. tokens per question

GPT-5.3-Codex circled · output tokens, reasoning included

Verification score

All models tested on the current suite

62 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price over $1

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
59GPT-5.3-Codex$0.01

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group (over $1) · higher is better

18 more models · see the full leaderboard

Time to first token

Peer group (over $1) · lower is better

20 more models · see the full leaderboard

End-to-end response time

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

Latency vs. output speed

GPT-5.3-Codex circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science28/30

Engineering11/15

Medicine7/11

Economics8/9

Law4/6

Humanities & social science8/9

More from OpenAI

OpenAI#12GPT-6 Astra76.2% verification score49 tok/s1.3 s first token$0.013 / question

OpenAI#12GPT-6.1 Terra Pro76.2% verification score— tok/s8.5 s first token$0.005 / question

OpenAI#12GPT-6.1 Sol76.2% verification score41 tok/s2.1 s first token$0.0029 / question

All OpenAI models →

Compare GPT-5.3-Codex

Head to head with its closest rivals, other OpenAI models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
Azure	$1.75	$14	400k	128k	—
OpenAI	$1.75	$14	400k	128k	—

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

GPT-5.3-Codex on OpenRouter: list prices and hosts
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

GPT-5.3-Codex: frequently asked questions

How accurate is GPT-5.3-Codex?: GPT-5.3-Codex answered 66 of 80 questions correctly (82.5%) in our 2026-10-27 run, ranking #3 of 78 models.
How fast is GPT-5.3-Codex?: GPT-5.3-Codex generated a median of 95 output tokens per second in our 2026-10-27 run, ranking #40 of 78. Median time to first token was 1.4 s.
What is the latency of GPT-5.3-Codex?: GPT-5.3-Codex had a median time to first token of 1.4 s in our 2026-10-27 run, ranking #57 of 78 models.
How much does GPT-5.3-Codex cost?: GPT-5.3-Codex cost $0.01 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is GPT-5.3-Codex API pricing?: GPT-5.3-Codex is listed at $1.75 per million input tokens and $14 per million output tokens on OpenRouter.
What is the context window of GPT-5.3-Codex?: GPT-5.3-Codex accepts up to 400,000 tokens of context, according to OpenRouter's model catalogue.
Who makes GPT-5.3-Codex?: GPT-5.3-Codex is made by OpenAI. We tested it through OpenRouter using the model ID openai/gpt-5.3-codex.
Where can I use GPT-5.3-Codex via API?: Through OpenRouter, GPT-5.3-Codex is served by 1 host: OpenAI.