Claude Sonnet 4.5 vs GPT-5.2 Codex
Claude Sonnet 4.5 and GPT-5.2 Codex are closely matched at 32.1 and 34.4 on the LLM Stats Score. GPT-5.2 Codex is 1.2x cheaper per token.
Anthropic · OpenAI · Updated for 2026
Which is better?
Claude Sonnet 4.5 and GPT-5.2 Codex are closely matched on the overall LLM Stats Score at 32.1 and 34.4.
On price, GPT-5.2 Codex is roughly 1.2x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
GPT-5.2 Codex also accepts a larger context window (400,000 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Claude Sonnet 4.5
- you want predictable pricing at $3.00/M input and $15.00/M output
Choose GPT-5.2 Codex
- cost matters — it's about 1.2x cheaper per token
- you process long inputs — it offers a 400,000 token context window
- you want the most recent training data — it shipped Jan 2026
At a glance
The differences that matter most.
Individual benchmarks
9 reported for Claude Sonnet 4.5 · 3 for GPT-5.2 Codex
Claude Sonnet 4.5 and GPT-5.2 Codexdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Claude Sonnet 4.5 ($3.00/1M tokens) is 1.7x more expensive than GPT-5.2 Codex ($1.75/1M tokens).
For output processing, Claude Sonnet 4.5 ($15.00/1M tokens) is 1.1x more expensive than GPT-5.2 Codex ($14.00/1M tokens).
In conclusion, Claude Sonnet 4.5 is more expensive than GPT-5.2 Codex.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
GPT-5.2 Codex accepts 400,000 input tokens compared to Claude Sonnet 4.5's 200,000 tokens. GPT-5.2 Codex can generate longer responses up to 128,000 tokens, while Claude Sonnet 4.5 is limited to 64,000 tokens.
Input capabilities
Documented input modalities across available providers
Both Claude Sonnet 4.5 and GPT-5.2 Codex support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Claude Sonnet 4.5
GPT-5.2 Codex
License
Usage and distribution terms
Both models are licensed under proprietary licenses.
Both models have usage restrictions defined by their respective organizations.
Proprietary
Closed source
Proprietary
Closed source
Release Timeline
When each model was launched
Claude Sonnet 4.5 was released on 2025-09-29, while GPT-5.2 Codex was released on 2026-01-14.
GPT-5.2 Codex is 4 months newer than Claude Sonnet 4.5.
Sep 29, 2025
11 months ago
Jan 14, 2026
8 months ago
3mo newerKnowledge Cutoff
When training data ends
Claude Sonnet 4.5 has a documented knowledge cutoff of 2025-01-31, while GPT-5.2 Codex's cutoff date is not specified.
We can confirm Claude Sonnet 4.5's training data extends to 2025-01-31, but cannot make a direct comparison without GPT-5.2 Codex's cutoff date.
Jan 2025
—
Provider Availability
Claude Sonnet 4.5 is available from Anthropic. GPT-5.2 Codex is available from OpenAI.
Claude Sonnet 4.5
GPT-5.2 Codex
Outputs Comparison
Judge for yourself.
Run your own prompts against Claude Sonnet 4.5 and GPT-5.2 Codex side-by-side, then vote on the output you prefer.
FAQ
Common questions about Claude Sonnet 4.5 vs GPT-5.2 Codex.