head-to-head

StepFun: Step 3.7 Flash vs Anthropic Claude Haiku Latest

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-22.

StepFun: Step 3.7 Flash Anthropic Claude Haiku Latest
Vendorstepfun~anthropic
Quality Score100100
Benchmark Score48.0-
Input Price$0.20/M$1.00/M
Output Price$1.15/M$5.00/M
Context Window256,000200,000
Max Output256,00064,000
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index49.1-
ai_index_agentic35.5-
ai_index_coding61.6-

Who wins by task?

TaskStepFun: Step 3.7 FlashAnthropic Claude Haiku Latest
SQL Generation 152 129
Code Review 145 124
Code Completion 129 114
Code Refactoring 143 124
Bug Fixing 154 128
Unit Test Generation 138 120
Code Documentation 132 122
Regex Writing 129 118
CI/CD Pipelines 131 116
Frontend Component Design 135 122
Data Analysis 149 124
CSV / Spreadsheet Cleanup 140 125
ETL Scripting 137 120
JSON Extraction 142 122
Bulk Data Labeling 133 120
OCR / Document Parsing 137 127
Table Extraction from PDFs 137 127
Long-Document Summarization 141 125
Short-Form Summarization 128 114
Blog Post Writing 129 117

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

Related comparisons

MoonshotAI: Kimi K2.7 Code vs StepFun: Step 3.7 Flash MoonshotAI: Kimi K2.7 Code vs Anthropic Claude Haiku Latest Qwen: Qwen3.7 Plus vs StepFun: Step 3.7 Flash Qwen: Qwen3.7 Plus vs Anthropic Claude Haiku Latest MiniMax: MiniMax M3 vs StepFun: Step 3.7 Flash MiniMax: MiniMax M3 vs Anthropic Claude Haiku Latest StepFun: Step 3.7 Flash vs xAI: Grok Build 0.1 StepFun: Step 3.7 Flash vs Google: Gemini 3.5 Flash