head-to-head

Anthropic: Claude Haiku Latest vs OpenAI: GPT-5.3-Codex

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

	Anthropic: Claude Haiku Latest	OpenAI: GPT-5.3-Codex
Vendor	~anthropic	openai
Quality Score	100	100
Benchmark Score	-	53.3
Input Price	$1.00/M	$1.75/M
Output Price	$5.00/M	$14.00/M
Context Window	200,000	400,000
Max Output	64,000	128,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	-	53.6

Who wins by task?

Task	Anthropic: Claude Haiku Latest	OpenAI: GPT-5.3-Codex
SQL Generation	129	138
Code Review	124	142
Code Completion	114	117
Code Refactoring	124	144
Bug Fixing	128	146
Unit Test Generation	120	130
Code Documentation	122	133
Regex Writing	118	122
CI/CD Pipelines	116	126
Frontend Component Design	122	128
Data Analysis	124	132
CSV / Spreadsheet Cleanup	125	134
ETL Scripting	120	135
JSON Extraction	122	120
Bulk Data Labeling	120	117
OCR / Document Parsing	127	133
Table Extraction from PDFs	127	133
Long-Document Summarization	125	145
Short-Form Summarization	114	115
Blog Post Writing	117	126

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