← All Models

Claude Sonnet 4.6 vs GPT-5.3-Codex

Claude Sonnet 4.6 leads in 4 of 8 categories

Arena ELO

Claude Sonnet 4.6

Cheaper

GPT-5.3-Codex

Faster

Claude Sonnet 4.6

Detailed Comparison

CategoryClaude Sonnet 4.6GPT-5.3-Codex
ProviderAnthropic OpenAI
Context Window1M WIN128K
Input Price ($/1M)$2 $1.75 WIN
Output Price ($/1M)$12 WIN$14
Arena ELO1440 WINN/A
Coding79.6% SWE-bench N/A
Reasoning72.5% OSWorld N/A
Speed (tokens/sec)~80 t/s WINN/A
Open SourceNo No

Frequently Asked Questions

Which is cheaper, Claude Sonnet 4.6 or GPT-5.3-Codex?

Claude Sonnet 4.6 is approximately 11% cheaper than GPT-5.3-Codex per million tokens.

Which is better for coding, Claude Sonnet 4.6 or GPT-5.3-Codex?

Claude Sonnet 4.6 scores 79.6% SWE-bench on coding benchmarks, while GPT-5.3-Codex scores N/A.

Which has a larger context window?

Claude Sonnet 4.6 supports 1M context, while GPT-5.3-Codex supports 128K.

Is Claude Sonnet 4.6 or GPT-5.3-Codex open source?

Claude Sonnet 4.6 is proprietary. GPT-5.3-Codex is proprietary.

Related Articles

Windows Codex and Claude Code fixes that work

Try Claude Opus 4.7 and read its benchmarks

Claude’s security test became a real breach

Claude’s 2026 limit changes are a capacity story, not a product story

Cognizant’s Claude play turns pilots into production

Prompt engineering is overrated for Claude Code

More Comparisons

Claude Sonnet 4.6 vs Claude Opus 4.5Claude Sonnet 4.6 vs Llama 4 ScoutClaude Sonnet 4.6 vs Claude Haiku 4.5Claude Sonnet 4.6 vs Qwen 3.6Claude Sonnet 4.6 vs Kimi K2.7 CodeClaude Sonnet 4.6 vs MiniMax H3Claude Sonnet 4.6 vs Llama 4 MaverickClaude Sonnet 4.6 vs Gemma 4GPT-5.3-Codex vs Claude Opus 4.5GPT-5.3-Codex vs Llama 4 ScoutGPT-5.3-Codex vs Claude Haiku 4.5GPT-5.3-Codex vs Qwen 3.6GPT-5.3-Codex vs Kimi K2.7 CodeGPT-5.3-Codex vs MiniMax H3GPT-5.3-Codex vs Llama 4 MaverickGPT-5.3-Codex vs Gemma 4