head-to-head

Thinking Machines: Inkling Small vs StepFun: Step 3.7 Flash

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

	Thinking Machines: Inkling Small	StepFun: Step 3.7 Flash
Vendor	thinkingmachines	stepfun
Quality Score	100	100
Benchmark Score	69.0	50.3
Input Price	$0.50/M	$0.20/M
Output Price	$1.20/M	$1.15/M
Context Window	524,288	262,144
Max Output	-	256,000
Tool Calling	✓	✓
Structured Output	-	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	✓	-
Benchmark Scores
ai_index	66.3	49.9
ai_index_agentic	50.8	35.5
ai_index_coding	87.4	65.3

Who wins by task?

Task	Thinking Machines: Inkling Small	StepFun: Step 3.7 Flash
SQL Generation	155	153
Code Review	155	146
Code Completion	133	130
Code Refactoring	154	144
Bug Fixing	169	155
Unit Test Generation	140	139
Code Documentation	140	133
Regex Writing	132	129
CI/CD Pipelines	135	131
Frontend Component Design	137	136
Data Analysis	156	150
CSV / Spreadsheet Cleanup	139	141
ETL Scripting	144	137
JSON Extraction	134	142
Bulk Data Labeling	130	133
OCR / Document Parsing	136	138
Table Extraction from PDFs	136	138
Long-Document Summarization	155	142
Short-Form Summarization	130	128
Blog Post Writing	136	129

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