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 2026-09-23.

StepFun: Step 3.7 Flash Google: Gemma 4 31B
Vendorstepfungoogle
Quality Score100100
Benchmark Score29.153.7
Input Price$0.20/M$0.09/M
Output Price$1.15/M$0.34/M
Context Window262,144262,144
Max Output230,40016,384
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index32.131.3
eqbench-70.8

Who wins by task?

TaskStepFun: Step 3.7 FlashGoogle: Gemma 4 31B
SQL Generation 135 139
Code Review 132 140
Code Completion 129 131
Code Refactoring 132 141
Bug Fixing 136 144
Unit Test Generation 125 130
Code Documentation 129 134
Regex Writing 122 125
CI/CD Pipelines 121 126
Frontend Component Design 125 128
Data Analysis 128 132
CSV / Spreadsheet Cleanup 129 133
ETL Scripting 127 133
JSON Extraction 131 131
Bulk Data Labeling 129 129
OCR / Document Parsing 129 131
Table Extraction from PDFs 129 131
Long-Document Summarization 134 143
Short-Form Summarization 125 126
Blog Post Writing 123 127

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

Related comparisons

Anthropic: Claude Haiku Latest vs Google: Gemma 4 31B Anthropic: Claude Sonnet 5 vs Google: Gemma 4 31B Anthropic: Claude Sonnet 5 vs StepFun: Step 3.7 Flash Anthropic: Claude Sonnet Latest vs Google: Gemma 4 31B ByteDance Seed: Seed-2.0-Code vs StepFun: Step 3.7 Flash ByteDance Seed: Seed 2.1 Turbo vs StepFun: Step 3.7 Flash Google: Gemini 3.1 Flash Lite vs Google: Gemma 4 31B Google: Gemini 3.5 Flash Lite vs Google: Gemma 4 31B

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.