head-to-head

Anthropic Claude Haiku Latest vs Google: Gemma 4 31B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-08-04.

	Anthropic Claude Haiku Latest	Google: Gemma 4 31B
Vendor	~anthropic	google
Quality Score	100	100
Benchmark Score	-	56.9
Input Price	$1.00/M	$0.10/M
Output Price	$5.00/M	$0.34/M
Context Window	200,000	262,144
Max Output	64,000	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 Haiku Latest	Google: Gemma 4 31B
SQL Generation	129	157
Code Review	124	154
Code Completion	114	132
Code Refactoring	124	152
Bug Fixing	128	161
Unit Test Generation	120	143
Code Documentation	122	138
Regex Writing	118	131
CI/CD Pipelines	116	136
Frontend Component Design	122	138
Data Analysis	124	152
CSV / Spreadsheet Cleanup	125	146
ETL Scripting	120	144
JSON Extraction	122	143
Bulk Data Labeling	120	133
OCR / Document Parsing	127	140
Table Extraction from PDFs	127	140
Long-Document Summarization	125	150
Short-Form Summarization	114	129
Blog Post Writing	117	134

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