Skip to main content

GPT-5.3 Codex

OpenAICurrentReleased Feb 5, 2026
Overall Score
Est. 86Prov. #13 of 119
Arena Elo
1416
Categories Ranked
8of 8
Price (1M tokens)
$1.75 in / $14 out
Speed
79tok/s
Context
400K
ProprietaryReasoning
Confidence
base

According to BenchLM.ai, GPT-5.3 Codex ranks #13 out of 119 models on the provisional leaderboard with an overall score of 86/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

GPT-5.3 Codex is a proprietary model with a 400K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

GPT-5.3 Codex sits inside the GPT-5.3 Codex family alongside GPT-5.3-Codex-Spark. This profile currently has 24 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Mathematics (#1), while its weakest is Agentic (#15). This performance profile makes it particularly strong for mathematical reasoning, scientific computing, and quantitative analysis.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#15
79.2/ 100
Weight: 22%7 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#9
87.5/ 100
Weight: 20%7 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#4
93.4/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#6
92.8/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#1
100.0/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#6
100.0/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#5
94.8/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#13
91.4/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1416

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

GPT-5.3 Codex Family

Base entry

Frequently Asked Questions

How does GPT-5.3 Codex perform overall in AI benchmarks?

GPT-5.3 Codex currently ranks #13 out of 119 models on BenchLM's provisional leaderboard with an overall score of 86 (estimated). It is created by OpenAI and features a 400K context window.

Is GPT-5.3 Codex good for knowledge and understanding?

GPT-5.3 Codex ranks #6 out of 119 models in knowledge and understanding benchmarks with an average score of 92.8. It is among the top performers in this category.

Is GPT-5.3 Codex good for coding and programming?

GPT-5.3 Codex ranks #9 out of 119 models in coding and programming benchmarks with an average score of 87.5. It is among the top performers in this category.

Is GPT-5.3 Codex good for reasoning and logic?

GPT-5.3 Codex ranks #4 out of 119 models in reasoning and logic benchmarks with an average score of 93.4. It is among the top performers in this category.

Is GPT-5.3 Codex good for agentic tool use and computer tasks?

GPT-5.3 Codex ranks #15 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 79.2. There are stronger options in this category.

Is GPT-5.3 Codex good for multimodal and grounded tasks?

GPT-5.3 Codex ranks #5 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 94.8. It is among the top performers in this category.

Is GPT-5.3 Codex good for instruction following?

GPT-5.3 Codex ranks #13 out of 119 models in instruction following benchmarks with an average score of 91.4. There are stronger options in this category.

Which sibling models are related to GPT-5.3 Codex?

GPT-5.3 Codex belongs to the GPT-5.3 Codex family. Related variants on BenchLM include GPT-5.3-Codex-Spark.

Does GPT-5.3 Codex have full benchmark coverage on BenchLM?

Not yet. GPT-5.3 Codex currently has 24 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

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

GPT-5.3 Codex has a context window of 400K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.