picksbymodel Get API access →
head-to-head

OpenAI: GPT-5.4 Mini 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 Mini Anthropic: Claude Sonnet 4.6
Vendoropenaianthropic
Quality Score100100
Benchmark Score37.769.7
Input Price$0.75/M$3.00/M
Output Price$4.50/M$15.00/M
Context Window400,0001,000,000
Max Output128,000128,000
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index39.749.6
aider_polyglot-61.3
eqbench-80.0

Who wins by task?

TaskOpenAI: GPT-5.4 MiniAnthropic: Claude Sonnet 4.6
SQL Generation 138 154
Code Review 139 161
Code Completion 131 120
Code Refactoring 142 162
Bug Fixing 143 166
Unit Test Generation 128 144
Code Documentation 134 142
Regex Writing 122 129
CI/CD Pipelines 124 138
Frontend Component Design 126 137
Data Analysis 130 147
CSV / Spreadsheet Cleanup 135 145
ETL Scripting 133 150
JSON Extraction 130 125
Bulk Data Labeling 128 118
OCR / Document Parsing 133 140
Table Extraction from PDFs 133 140
Long-Document Summarization 143 161
Short-Form Summarization 124 118
Blog Post Writing 126 137

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

Related comparisons

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