picksbymodel Get API access →
head-to-head

OpenAI: GPT-5.4 vs Anthropic: Claude Sonnet 4.6

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-23.

OpenAI: GPT-5.4 Anthropic: Claude Sonnet 4.6
Vendoropenaianthropic
Quality Score100100
Benchmark Score80.969.7
Input Price$2.50/M$3.00/M
Output Price$15.00/M$15.00/M
Context Window1,050,0001,000,000
Max Output128,000128,000
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index64.349.6
aider_polyglot-61.3
eqbench82.480.0

Who wins by task?

TaskOpenAI: GPT-5.4Anthropic: Claude Sonnet 4.6
SQL Generation 145 154
Code Review 154 161
Code Completion 120 120
Code Refactoring 157 162
Bug Fixing 158 166
Unit Test Generation 137 144
Code Documentation 140 142
Regex Writing 126 129
CI/CD Pipelines 133 138
Frontend Component Design 133 137
Data Analysis 138 147
CSV / Spreadsheet Cleanup 139 145
ETL Scripting 145 150
JSON Extraction 120 125
Bulk Data Labeling 116 118
OCR / Document Parsing 136 140
Table Extraction from PDFs 136 140
Long-Document Summarization 157 161
Short-Form Summarization 117 118
Blog Post Writing 133 137

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Anthropic: Claude Haiku Latest vs OpenAI: GPT-5.4 Anthropic: Claude Sonnet 5 vs OpenAI: GPT-5.4 Anthropic: Claude Sonnet Latest vs Anthropic: Claude Sonnet 4.6 Anthropic: Claude Sonnet Latest vs OpenAI: GPT-5.4 ByteDance Seed: Seed-2.0-Lite vs Anthropic: Claude Sonnet 4.6 ByteDance Seed: Seed-2.0-Lite vs OpenAI: GPT-5.4 Google: Gemini 3.1 Flash Lite Preview vs Anthropic: Claude Sonnet 4.6 Google: Gemini 3.1 Flash Lite vs Anthropic: Claude Sonnet 4.6

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.