picksbymodel Get API access →
head-to-head

Google: Gemma 4 26B A4B (free) vs Google: Gemma 4 31B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-23.

Google: Gemma 4 26B A4B (free) Google: Gemma 4 31B
Vendorgooglegoogle
Quality Score100100
Benchmark Score50.953.7
Input PriceFree$0.09/M
Output PriceFree$0.34/M
Context Window262,144262,144
Max Output32,76816,384
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index27.531.3
eqbench70.070.8

Who wins by task?

TaskGoogle: Gemma 4 26B A4B (free)Google: Gemma 4 31B
SQL Generation 139 139
Code Review 140 140
Code Refactoring 141 141
Bug Fixing 144 144
Unit Test Generation 129 130
Code Documentation 134 134
Regex Writing 125 125
CI/CD Pipelines 125 126
Frontend Component Design 128 128
Data Analysis 132 132
CSV / Spreadsheet Cleanup 133 133
ETL Scripting 133 133
JSON Extraction 132 131
Bulk Data Labeling 130 129
OCR / Document Parsing 131 131
Table Extraction from PDFs 131 131
Long-Document Summarization 143 143
Short-Form Summarization 126 126
Blog Post Writing 127 127

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

Related comparisons

Anthropic: Claude Haiku Latest vs Google: Gemma 4 26B A4B (free) Anthropic: Claude Haiku Latest vs Google: Gemma 4 31B Anthropic: Claude Sonnet 5 vs Google: Gemma 4 26B A4B (free) Anthropic: Claude Sonnet 5 vs Google: Gemma 4 31B Anthropic: Claude Sonnet Latest vs Google: Gemma 4 26B A4B (free) Anthropic: Claude Sonnet Latest vs Google: Gemma 4 31B Google: Gemini 3.1 Flash Lite vs Google: Gemma 4 26B A4B (free) Google: Gemini 3.1 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.