head-to-head

Anthropic: Claude Sonnet Latest vs Google: Gemini 3.1 Pro Preview

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

	Anthropic: Claude Sonnet Latest	Google: Gemini 3.1 Pro Preview
Vendor	~anthropic	google
Quality Score	100	100
Benchmark Score	-	66.5
Input Price	$2.00/M	$2.00/M
Output Price	$10.00/M	$12.00/M
Context Window	1,000,000	1,048,576
Max Output	128,000	65,536
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	✓
Benchmark Scores
ai_index	-	49.0
eqbench	-	74.3

Who wins by task?

Task	Anthropic: Claude Sonnet Latest	Google: Gemini 3.1 Pro Preview
SQL Generation	132	143
Code Review	132	150
Code Completion	117	120
Code Refactoring	136	153
Bug Fixing	136	154
Unit Test Generation	124	135
Code Documentation	129	139
Regex Writing	117	125
CI/CD Pipelines	120	131
Frontend Component Design	122	130
Data Analysis	124	135
CSV / Spreadsheet Cleanup	132	139
ETL Scripting	128	142
JSON Extraction	121	121
Bulk Data Labeling	118	117
OCR / Document Parsing	131	135
Table Extraction from PDFs	131	135
Long-Document Summarization	136	154
Short-Form Summarization	113	117
Blog Post Writing	120	131

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