head-to-head

OpenAI: GPT-5.6 Luna vs Anthropic: Claude Haiku Latest

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

	OpenAI: GPT-5.6 Luna	Anthropic: Claude Haiku Latest
Vendor	openai	~anthropic
Quality Score	100	100
Benchmark Score	62.3	-
Input Price	$0.20/M	$1.00/M
Output Price	$1.20/M	$5.00/M
Context Window	1,050,000	200,000
Max Output	128,000	64,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	61.6	-

Who wins by task?

Task	OpenAI: GPT-5.6 Luna	Anthropic: Claude Haiku Latest
SQL Generation	141	129
Code Review	143	124
Code Completion	133	114
Code Refactoring	145	124
Bug Fixing	147	128
Unit Test Generation	131	120
Code Documentation	137	122
Regex Writing	125	118
CI/CD Pipelines	127	116
Frontend Component Design	129	122
Data Analysis	133	124
CSV / Spreadsheet Cleanup	136	125
ETL Scripting	136	120
JSON Extraction	131	122
Bulk Data Labeling	129	120
OCR / Document Parsing	134	127
Table Extraction from PDFs	134	127
Long-Document Summarization	147	125
Short-Form Summarization	126	114
Blog Post Writing	129	117

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