Google: Gemma 4 31B (free) vs MoonshotAI: Kimi K2.5
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Google: Gemma 4 31B (free) | MoonshotAI: Kimi K2.5 | |
|---|---|---|
| Vendor | moonshotai | |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.7 | 64.3 |
| Input Price | Free | $0.53/M |
| Output Price | Free | $3.33/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 32,768 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 48.4 | 62.9 |
| ai_index_agentic | 23.8 | - |
| ai_index_coding | 71.7 | - |
| eqbench | 57.5 | 55.2 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemma 4 31B (free) costs $0 and Kimi K2.5 costs $1.36, so Gemma 4 31B (free) is free for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
Only Gemma 4 31B (free) offers video input.
On our blended benchmark score Kimi K2.5 leads 64.3 to 53.7.
Across the 20 tasks where they differ, Gemma 4 31B (free) scores higher on 20 (SQL Generation, Code Review, Code Completion and others).
Gemma 4 31B (free) was released in April 2026 and Kimi K2.5 in January 2026.
Pick Gemma 4 31B (free) if you need lower cost, video input or the stronger all-round task scores; pick Kimi K2.5 if you need benchmark performance.
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) | MoonshotAI: Kimi K2.5 |
|---|---|---|
| SQL Generation | 156 | 142 |
| Code Review | 152 | 145 |
| Code Completion | 131 | 131 |
| Code Refactoring | 151 | 145 |
| Bug Fixing | 160 | 149 |
| Unit Test Generation | 143 | 132 |
| Code Documentation | 137 | 135 |
| Regex Writing | 131 | 127 |
| CI/CD Pipelines | 135 | 128 |
| Frontend Component Design | 138 | 131 |
| Data Analysis | 152 | 136 |
| CSV / Spreadsheet Cleanup | 145 | 133 |
| ETL Scripting | 143 | 136 |
| JSON Extraction | 143 | 131 |
| Bulk Data Labeling | 133 | 128 |
| OCR / Document Parsing | 140 | 133 |
| Table Extraction from PDFs | 140 | 133 |
| Long-Document Summarization | 149 | 146 |
| Short-Form Summarization | 129 | 127 |
| Blog Post Writing | 133 | 130 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →