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 2026-09-23.

StepFun: Step 3.7 Flash Anthropic: Claude Haiku Latest
Vendorstepfun~anthropic
Quality Score100100
Benchmark Score29.1-
Input Price$0.20/M$1.00/M
Output Price$1.15/M$5.00/M
Context Window262,144200,000
Max Output230,40064,000
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index32.1-

Who wins by task?

TaskStepFun: Step 3.7 FlashAnthropic: Claude Haiku Latest
SQL Generation 135 129
Code Review 132 124
Code Completion 129 114
Code Refactoring 132 124
Bug Fixing 136 128
Unit Test Generation 125 120
Code Documentation 129 122
Regex Writing 122 118
CI/CD Pipelines 121 116
Frontend Component Design 125 122
Data Analysis 128 124
CSV / Spreadsheet Cleanup 129 125
ETL Scripting 127 120
JSON Extraction 131 122
Bulk Data Labeling 129 120
OCR / Document Parsing 129 127
Table Extraction from PDFs 129 127
Long-Document Summarization 134 125
Short-Form Summarization 125 114
Blog Post Writing 123 117

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

Related comparisons

Anthropic: Claude Haiku Latest vs Anthropic: Claude Sonnet Latest Anthropic: Claude Haiku Latest vs ByteDance Seed: Seed-2.0-Lite Anthropic: Claude Haiku Latest vs ByteDance Seed: Seed-2.0-Mini Anthropic: Claude Haiku Latest vs Google: Gemini 3.1 Flash Lite Preview Anthropic: Claude Haiku Latest vs Google: Gemini 3.1 Pro Preview Anthropic: Claude Haiku Latest vs Google: Gemini 3.1 Pro Preview Custom Tools Anthropic: Claude Haiku Latest vs Google: Gemini Flash Latest Anthropic: Claude Haiku Latest vs Google: Gemini Pro Latest

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.