head-to-head

Anthropic Claude Haiku Latest vs Google: Gemma 4 26B A4B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-22.

	Anthropic Claude Haiku Latest	Google: Gemma 4 26B A4B
Vendor	~anthropic	google
Quality Score	100	100
Benchmark Score	-	51.0
Input Price	$1.00/M	$0.06/M
Output Price	$5.00/M	$0.33/M
Context Window	200,000	262,144
Max Output	64,000	-
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	-	42.4
ai_index_agentic	-	18.1
ai_index_coding	-	64.9
eqbench	-	70.0

Who wins by task?

Task	Anthropic Claude Haiku Latest	Google: Gemma 4 26B A4B
SQL Generation	129	154
Code Review	124	151
Code Completion	114	132
Code Refactoring	124	150
Bug Fixing	128	158
Unit Test Generation	120	141
Code Documentation	122	137
Regex Writing	118	130
CI/CD Pipelines	116	134
Frontend Component Design	122	137
Data Analysis	124	149
CSV / Spreadsheet Cleanup	125	144
ETL Scripting	120	142
JSON Extraction	122	142
Bulk Data Labeling	120	133
OCR / Document Parsing	127	139
Table Extraction from PDFs	127	139
Long-Document Summarization	125	149
Short-Form Summarization	114	129
Blog Post Writing	117	132

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