head-to-head

Anthropic: Claude Sonnet 5 vs OpenAI: GPT-5.4

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

Anthropic: Claude Sonnet 5 OpenAI: GPT-5.4
Vendoranthropicopenai
Quality Score100100
Benchmark Score63.980.9
Input Price$2.00/M$2.50/M
Output Price$10.00/M$15.00/M
Context Window1,000,0001,050,000
Max Output128,000128,000
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index63.064.3
eqbench-82.4

Who wins by task?

TaskAnthropic: Claude Sonnet 5OpenAI: GPT-5.4
SQL Generation 140 145
Code Review 144 154
Code Completion 118 120
Code Refactoring 146 157
Bug Fixing 148 158
Unit Test Generation 131 137
Code Documentation 135 140
Regex Writing 123 126
CI/CD Pipelines 127 133
Frontend Component Design 129 133
Data Analysis 133 138
CSV / Spreadsheet Cleanup 135 139
ETL Scripting 136 145
JSON Extraction 121 120
Bulk Data Labeling 118 116
OCR / Document Parsing 134 136
Table Extraction from PDFs 134 136
Long-Document Summarization 146 157
Short-Form Summarization 116 117
Blog Post Writing 128 133

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

Related comparisons

Anthropic: Claude Haiku Latest vs OpenAI: GPT-5.4 Anthropic: Claude Opus 5 (batch) vs Anthropic: Claude Sonnet 5 Anthropic: Claude Sonnet 5 vs Anthropic: Claude Haiku Latest Anthropic: Claude Sonnet 5 vs Anthropic: Claude Opus 4.8 (batch) Anthropic: Claude Sonnet 5 vs Anthropic: Claude Sonnet 5 (batch) Anthropic: Claude Sonnet 5 vs Anthropic: Claude Sonnet Latest Anthropic: Claude Sonnet 5 vs ByteDance Seed: Seed-2.0-Lite Anthropic: Claude Sonnet 5 vs ByteDance Seed: Seed-2.0-Mini

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.