picksbymodel Get API access →
head-to-head

StepFun: Step 3.7 Flash vs Google: Gemma 4 31B

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

StepFun: Step 3.7 Flash Google: Gemma 4 31B
Vendorstepfungoogle
Quality Score100100
Benchmark Score50.857.2
Input Price$0.20/M$0.12/M
Output Price$1.15/M$0.35/M
Context Window256,000262,144
Max Output256,000262,144
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index49.948.4
ai_index_agentic35.523.8
ai_index_coding65.371.7
eqbench-70.8

Who wins by task?

TaskStepFun: Step 3.7 FlashGoogle: Gemma 4 31B
SQL Generation 153 157
Code Review 146 154
Code Completion 129 132
Code Refactoring 143 152
Bug Fixing 155 161
Unit Test Generation 139 143
Code Documentation 132 138
Regex Writing 129 131
CI/CD Pipelines 131 136
Frontend Component Design 136 138
Data Analysis 150 152
CSV / Spreadsheet Cleanup 141 146
ETL Scripting 137 144
JSON Extraction 142 143
Bulk Data Labeling 133 133
OCR / Document Parsing 137 140
Table Extraction from PDFs 137 140
Long-Document Summarization 142 150
Short-Form Summarization 128 129
Blog Post Writing 129 134

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

Related comparisons

OpenAI: GPT-5.6 Luna Pro vs StepFun: Step 3.7 Flash OpenAI: GPT-5.6 Luna Pro vs Google: Gemma 4 31B OpenAI: GPT-5.6 Luna vs StepFun: Step 3.7 Flash OpenAI: GPT-5.6 Luna vs Google: Gemma 4 31B OpenAI: GPT-5.6 Terra Pro vs StepFun: Step 3.7 Flash OpenAI: GPT-5.6 Terra Pro vs Google: Gemma 4 31B OpenAI: GPT-5.6 Terra vs StepFun: Step 3.7 Flash OpenAI: GPT-5.6 Terra vs Google: Gemma 4 31B