head-to-head

Thinking Machines: Inkling Small vs Anthropic: Claude Sonnet 5

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-08-01.

	Thinking Machines: Inkling Small	Anthropic: Claude Sonnet 5
Vendor	thinkingmachines	anthropic
Quality Score	100	100
Benchmark Score	69.0	90.4
Input Price	$0.50/M	$2.00/M
Output Price	$1.20/M	$10.00/M
Context Window	524,288	1,000,000
Max Output	-	128,000
Tool Calling	✓	✓
Structured Output	-	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	✓	-
Benchmark Scores
ai_index	66.3	88.0
ai_index_agentic	50.8	77.0
ai_index_coding	87.4	100.0

Who wins by task?

Task	Thinking Machines: Inkling Small	Anthropic: Claude Sonnet 5
SQL Generation	155	171
Code Review	155	167
Code Completion	133	119
Code Refactoring	154	164
Bug Fixing	169	180
Unit Test Generation	140	154
Code Documentation	140	141
Regex Writing	132	135
CI/CD Pipelines	135	144
Frontend Component Design	137	146
Data Analysis	156	171
CSV / Spreadsheet Cleanup	139	153
ETL Scripting	144	154
JSON Extraction	134	138
Bulk Data Labeling	130	124
OCR / Document Parsing	136	146
Table Extraction from PDFs	136	146
Long-Document Summarization	155	159
Short-Form Summarization	130	122
Blog Post Writing	136	140

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