picksbymodel Get API access →
head-to-head

Anthropic: Claude Sonnet 5 vs Google: Gemini 3.5 Flash (batch)

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-07-30.

Anthropic: Claude Sonnet 5 Google: Gemini 3.5 Flash (batch)
Vendoranthropicgoogle
Quality Score100100
Benchmark Score90.483.3
Input Price$2.00/M$0.75/M
Output Price$10.00/M$4.50/M
Context Window1,000,0001,048,576
Max Output128,00065,536
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio-✓
Benchmark Scores
ai_index88.082.8
ai_index_agentic77.061.8
ai_index_coding100.0100.0

Who wins by task?

TaskAnthropic: Claude Sonnet 5Google: Gemini 3.5 Flash (batch)
SQL Generation 171 169
Code Review 167 164
Code Completion 119 132
Code Refactoring 164 162
Bug Fixing 180 176
Unit Test Generation 154 152
Code Documentation 141 142
Regex Writing 135 134
CI/CD Pipelines 144 143
Frontend Component Design 146 145
Data Analysis 171 167
ETL Scripting 154 152
JSON Extraction 138 147
Bulk Data Labeling 124 134
OCR / Document Parsing 146 146
Table Extraction from PDFs 146 146
Long-Document Summarization 159 158
Short-Form Summarization 122 130
Blog Post Writing 140 139

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

Related comparisons

Qwen: Qwen3.7 Flash vs Anthropic: Claude Sonnet 5 Qwen: Qwen3.7 Flash vs Google: Gemini 3.5 Flash (batch) Google: Gemini 3.6 Flash vs Anthropic: Claude Sonnet 5 Google: Gemini 3.6 Flash vs Google: Gemini 3.5 Flash (batch) Google: Gemini 3.6 Flash (batch) vs Anthropic: Claude Sonnet 5 Google: Gemini 3.6 Flash (batch) vs Google: Gemini 3.5 Flash (batch) Google: Gemini 3.5 Flash Lite vs Anthropic: Claude Sonnet 5 Google: Gemini 3.5 Flash Lite vs Google: Gemini 3.5 Flash (batch)