Google: Gemma 4 31B (free) vs OpenAI: GPT-5.4 Mini
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Google: Gemma 4 31B (free) | OpenAI: GPT-5.4 Mini | |
|---|---|---|
| Vendor | openai | |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.7 | 70.8 |
| Input Price | Free | $0.75/M |
| Output Price | Free | $4.50/M |
| Context Window | 262,144 | 400,000 |
| Max Output | 32,768 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 48.4 | 66.0 |
| ai_index_agentic | 23.8 | 49.8 |
| ai_index_coding | 71.7 | 92.5 |
| eqbench | 57.5 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemma 4 31B (free) costs $0 and GPT-5.4 Mini costs $1.88, so Gemma 4 31B (free) is free for the same work.
GPT-5.4 Mini reads up to 400,000 tokens at once, roughly 600 pages of text, against about 393 pages for Gemma 4 31B (free).
Only Gemma 4 31B (free) offers video input.
On our blended benchmark score GPT-5.4 Mini leads 70.8 to 53.7.
Across the 20 tasks where they differ, Gemma 4 31B (free) scores higher on 2 (Bulk Data Labeling, Short-Form Summarization), GPT-5.4 Mini on 18 (SQL Generation, Code Review, Code Completion and others).
Gemma 4 31B (free) was released in April 2026 and GPT-5.4 Mini in March 2026.
Pick Gemma 4 31B (free) if you need lower cost or video input; pick GPT-5.4 Mini if you need long documents, benchmark performance or the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | Google: Gemma 4 31B (free) | OpenAI: GPT-5.4 Mini |
|---|---|---|
| SQL Generation | 156 | 164 |
| Code Review | 152 | 159 |
| Code Completion | 131 | 132 |
| Code Refactoring | 151 | 158 |
| Bug Fixing | 160 | 170 |
| Unit Test Generation | 143 | 148 |
| Code Documentation | 137 | 140 |
| Regex Writing | 131 | 132 |
| CI/CD Pipelines | 135 | 139 |
| Frontend Component Design | 138 | 141 |
| Data Analysis | 152 | 160 |
| CSV / Spreadsheet Cleanup | 145 | 151 |
| ETL Scripting | 143 | 149 |
| JSON Extraction | 143 | 146 |
| Bulk Data Labeling | 133 | 133 |
| OCR / Document Parsing | 140 | 144 |
| Table Extraction from PDFs | 140 | 144 |
| Long-Document Summarization | 149 | 154 |
| Short-Form Summarization | 129 | 129 |
| Blog Post Writing | 133 | 136 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →