head-to-head

Google: Gemini 3.5 Flash Lite vs Anthropic: Claude Haiku Latest

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

	Google: Gemini 3.5 Flash Lite	Anthropic: Claude Haiku Latest
Vendor	google	~anthropic
Quality Score	100	100
Benchmark Score	34.2	-
Input Price	$0.30/M	$1.00/M
Output Price	$2.50/M	$5.00/M
Context Window	1,048,576	200,000
Max Output	65,536	64,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	✓	-
Benchmark Scores
ai_index	36.6	-

Who wins by task?

Task	Google: Gemini 3.5 Flash Lite	Anthropic: Claude Haiku Latest
SQL Generation	138	129
Code Review	139	124
Code Completion	132	114
Code Refactoring	141	124
Bug Fixing	143	128
Unit Test Generation	128	120
Code Documentation	134	122
Regex Writing	123	118
CI/CD Pipelines	124	116
Frontend Component Design	126	122
Data Analysis	129	124
CSV / Spreadsheet Cleanup	135	125
ETL Scripting	133	120
JSON Extraction	131	122
Bulk Data Labeling	129	120
OCR / Document Parsing	132	127
Table Extraction from PDFs	132	127
Long-Document Summarization	143	125
Short-Form Summarization	125	114
Blog Post Writing	126	117

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