head-to-head

StepFun: Step 3.7 Flash vs Anthropic Claude Sonnet Latest

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-07-15.

	StepFun: Step 3.7 Flash	Anthropic Claude Sonnet Latest
Vendor	stepfun	~anthropic
Quality Score	100	100
Benchmark Score	50.8	-
Input Price	$0.20/M	$2.00/M
Output Price	$1.15/M	$10.00/M
Context Window	256,000	1,000,000
Max Output	256,000	128,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	49.9	-
ai_index_agentic	35.5	-
ai_index_coding	65.3	-

Who wins by task?

Task	StepFun: Step 3.7 Flash	Anthropic Claude Sonnet Latest
SQL Generation	153	132
Code Review	146	132
Code Completion	129	117
Code Refactoring	143	136
Bug Fixing	155	136
Unit Test Generation	139	124
Code Documentation	132	129
Regex Writing	129	117
CI/CD Pipelines	131	120
Frontend Component Design	136	122
Data Analysis	150	124
CSV / Spreadsheet Cleanup	141	132
ETL Scripting	137	128
JSON Extraction	142	121
Bulk Data Labeling	133	118
OCR / Document Parsing	137	131
Table Extraction from PDFs	137	131
Long-Document Summarization	142	136
Short-Form Summarization	128	113
Blog Post Writing	129	120

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