head-to-head

Google: Gemini 3.6 Flash (batch) vs Anthropic: Claude Sonnet 5 (batch)

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-07-29.

Google: Gemini 3.6 Flash (batch) Anthropic: Claude Sonnet 5 (batch)
Vendorgoogleanthropic
Quality Score100100
Benchmark Score83.990.4
Input Price$0.75/M$1.00/M
Output Price$3.75/M$5.00/M
Context Window1,048,5761,000,000
Max Output65,536128,000
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio-
Benchmark Scores
ai_index82.688.0
ai_index_agentic63.977.0
ai_index_coding100.0100.0

Who wins by task?

TaskGoogle: Gemini 3.6 Flash (batch)Anthropic: Claude Sonnet 5 (batch)
SQL Generation 169 171
Code Review 165 167
Code Completion 132 120
Code Refactoring 162 164
Bug Fixing 177 180
Unit Test Generation 153 154
Code Documentation 142 143
Regex Writing 135 136
CI/CD Pipelines 143 144
Frontend Component Design 145 146
Data Analysis 167 171
CSV / Spreadsheet Cleanup 153 154
ETL Scripting 153 154
JSON Extraction 148 140
Bulk Data Labeling 134 126
OCR / Document Parsing 146 146
Table Extraction from PDFs 146 146
Long-Document Summarization 158 160
Short-Form Summarization 131 123
Blog Post Writing 139 140

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

Related comparisons

Qwen: Qwen3.7 Flash vs Google: Gemini 3.6 Flash (batch) Qwen: Qwen3.7 Flash vs Anthropic: Claude Sonnet 5 (batch) Google: Gemini 3.6 Flash vs Google: Gemini 3.6 Flash (batch) Google: Gemini 3.6 Flash vs Anthropic: Claude Sonnet 5 (batch) Google: Gemini 3.6 Flash (batch) vs Google: Gemini 3.5 Flash Lite Google: Gemini 3.6 Flash (batch) vs Google: Gemini 3.5 Flash Lite (batch) Google: Gemini 3.6 Flash (batch) vs Thinking Machines: Inkling Google: Gemini 3.6 Flash (batch) vs Meta: Muse Spark 1.1