head-to-head

Thinking Machines: Inkling Small vs Anthropic: Claude Sonnet 5 (batch)

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-08-13.

	Thinking Machines: Inkling Small	Anthropic: Claude Sonnet 5 (batch)
Vendor	thinkingmachines	anthropic
Quality Score	100	100
Benchmark Score	69.1	91.6
Input Price	$0.45/M	$1.00/M
Output Price	$1.20/M	$5.00/M
Context Window	524,288	1,000,000
Max Output	262,144	128,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	✓	-
Benchmark Scores
ai_index	67.9	91.2
ai_index_agentic	52.6	82.0
ai_index_coding	87.4	100.0

Who wins by task?

Task	Thinking Machines: Inkling Small	Anthropic: Claude Sonnet 5 (batch)
SQL Generation	164	172
Code Review	159	168
Code Completion	133	120
Code Refactoring	158	165
Bug Fixing	170	182
Unit Test Generation	148	155
Code Documentation	141	143
Regex Writing	133	136
CI/CD Pipelines	139	145
Frontend Component Design	141	147
Data Analysis	160	172
CSV / Spreadsheet Cleanup	151	154
ETL Scripting	149	155
JSON Extraction	146	140
Bulk Data Labeling	134	126
OCR / Document Parsing	144	147
Table Extraction from PDFs	144	147
Long-Document Summarization	155	160
Short-Form Summarization	130	123
Blog Post Writing	136	141

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