The AI arena is free today

Open Superagent

GPT-5.2 Codex vs GPT-5.3 Codex

GPT-5.2 Codex and GPT-5.3 Codex are closely matched at 34.6 and 36.8 on the LLM Stats Score. GPT-5.2 Codex and GPT-5.3 Codex cost the same.

OpenAI · OpenAI · Updated for 2026

Which is better?

GPT-5.2 Codex and GPT-5.3 Codex are closely matched on the overall LLM Stats Score at 34.6 and 36.8.

In the 3 individual benchmarks reported for both models, GPT-5.3 Codex wins 2; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose GPT-5.2 Codex

  • you want predictable pricing at $1.75/M input and $14.00/M output

Choose GPT-5.3 Codex

  • you value its reported benchmark strengths — it wins 2 of 3 exact shared results
  • you want the most recent training data — it shipped Feb 2026

At a glance

The differences that matter most.

Core performance indexes
34.6
#81
36.8
#66
34.9
#76
37.5
#61
25.1
#61
30.1
#45
18.9
#56
22.8
#48
Cost, coverage & limits
Benchmark wins
1 of 3
2 of 3
Input price
$1.75 / M
$1.75 / M
Output price
$14.00 / M
$14.00 / M
Context window
400,000
400,000

Individual benchmarks

3 reported for GPT-5.2 Codex · 6 for GPT-5.3 Codex

3 shared

GPT-5.2 Codex outperforms in 1 benchmarks (LiveBench), while GPT-5.3 Codex is better at 2 benchmarks (SWE-Bench Pro, Terminal-Bench 2.0).

GPT-5.3 Codex shows notably better performance in the majority of benchmarks.

Tue Sep 01 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

For input processing, GPT-5.2 Codex ($1.75/1M tokens) costs the same as GPT-5.3 Codex ($1.75/1M tokens).

For output processing, GPT-5.2 Codex ($14.00/1M tokens) costs the same as GPT-5.3 Codex ($14.00/1M tokens).

In conclusion, GPT-5.2 Codex and GPT-5.3 Codex cost the same.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Sep 01 2026 • llm-stats.com
OpenAI
GPT-5.2 Codex
Input tokens$1.75
Output tokens$14.00
Best providerOpenAI
OpenAI
GPT-5.3 Codex
Input tokens$1.75
Output tokens$14.00
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Both models have the same input context window of 400,000 tokens. Both models can generate responses up to 128,000 tokens.

OpenAI
GPT-5.2 Codex
Input400,000 tokens
Output128,000 tokens
OpenAI
GPT-5.3 Codex
Input400,000 tokens
Output128,000 tokens
Tue Sep 01 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both GPT-5.2 Codex and GPT-5.3 Codex support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

GPT-5.2 Codex

Text
Images
Audio
Video

GPT-5.3 Codex

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

GPT-5.2 Codex

Proprietary

Closed source

GPT-5.3 Codex

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.2 Codex was released on 2026-01-14, while GPT-5.3 Codex was released on 2026-02-05.

GPT-5.3 Codex is 1 month newer than GPT-5.2 Codex.

GPT-5.2 Codex

Jan 14, 2026

7 months ago

GPT-5.3 Codex

Feb 5, 2026

6 months ago

3w newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

GPT-5.2 Codex is available from OpenAI. GPT-5.3 Codex is available from OpenAI.

GPT-5.2 Codex

openai logo
OpenAI
Input Price:Input: $1.75/1MOutput Price:Output: $14.00/1M

GPT-5.3 Codex

openai logo
OpenAI
Input Price:Input: $1.75/1MOutput Price:Output: $14.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-5.2 Codex and GPT-5.3 Codex side-by-side, then vote on the output you prefer.

GPT-5.2 Codex
✓ Preferred
GPT-5.3 Codex
Open in Playground

FAQ

Common questions about GPT-5.2 Codex vs GPT-5.3 Codex.

Which is better, GPT-5.2 Codex or GPT-5.3 Codex?

GPT-5.2 Codex and GPT-5.3 Codex are closely matched on the LLM Stats Score at 34.6 and 36.8. GPT-5.2 Codex is made by OpenAI and GPT-5.3 Codex is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-5.2 Codex compare to GPT-5.3 Codex in benchmarks?

GPT-5.2 Codex scores LiveBench: 74.3%, Terminal-Bench 2.0: 64.0%, SWE-Bench Pro: 56.4%. GPT-5.3 Codex scores SWE-Lancer (IC-Diamond subset): 81.4%, Cybersecurity CTFs: 77.6%, Terminal-Bench 2.0: 77.3%, LiveBench: 72.8%, OSWorld-Verified: 64.7%.

Is GPT-5.2 Codex cheaper than GPT-5.3 Codex?

Both models cost $1.75 per million input tokens.

What are the context window sizes for GPT-5.2 Codex and GPT-5.3 Codex?

GPT-5.2 Codex supports 400K tokens and GPT-5.3 Codex supports 400K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5.2 Codex and GPT-5.3 Codex?

Key differences include LLM Stats Score (34.6 vs 36.8). See the full comparison above for benchmark-by-benchmark results.