head-to-head

Anthropic: Claude Haiku 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 Haiku Latest	Google: Gemini 3.1 Pro Preview
Vendor	~anthropic	google
Quality Score	100	100
Benchmark Score	-	66.5
Input Price	$1.00/M	$2.00/M
Output Price	$5.00/M	$12.00/M
Context Window	200,000	1,048,576
Max Output	64,000	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 Haiku Latest	Google: Gemini 3.1 Pro Preview
SQL Generation	129	143
Code Review	124	150
Code Completion	114	120
Code Refactoring	124	153
Bug Fixing	128	154
Unit Test Generation	120	135
Code Documentation	122	139
Regex Writing	118	125
CI/CD Pipelines	116	131
Frontend Component Design	122	130
Data Analysis	124	135
CSV / Spreadsheet Cleanup	125	139
ETL Scripting	120	142
JSON Extraction	122	121
Bulk Data Labeling	120	117
OCR / Document Parsing	127	135
Table Extraction from PDFs	127	135
Long-Document Summarization	125	154
Short-Form Summarization	114	117
Blog Post Writing	117	131

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