head-to-head

Anthropic Claude Sonnet Latest vs Google: Gemma 4 31B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-23.

	Anthropic Claude Sonnet Latest	Google: Gemma 4 31B
Vendor	~anthropic	google
Quality Score	100	100
Benchmark Score	-	56.4
Input Price	$3.00/M	$0.12/M
Output Price	$15.00/M	$0.35/M
Context Window	1,000,000	262,144
Max Output	128,000	262,144
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	-	48.4
ai_index_agentic	-	23.8
ai_index_coding	-	71.7
eqbench	-	70.8

Who wins by task?

Task	Anthropic Claude Sonnet Latest	Google: Gemma 4 31B
SQL Generation	132	157
Code Review	132	154
Code Completion	116	132
Code Refactoring	136	152
Bug Fixing	136	161
Unit Test Generation	124	143
Code Documentation	128	138
Regex Writing	116	131
CI/CD Pipelines	120	136
Frontend Component Design	122	138
Data Analysis	124	152
CSV / Spreadsheet Cleanup	132	146
ETL Scripting	128	144
JSON Extraction	120	143
Bulk Data Labeling	116	133
OCR / Document Parsing	131	140
Table Extraction from PDFs	131	140
Long-Document Summarization	136	150
Short-Form Summarization	112	129
Blog Post Writing	120	134

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