head-to-head
Anthropic Claude Haiku Latest vs Google: Gemma 4 31B (free)
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-20.
| Anthropic Claude Haiku Latest | Google: Gemma 4 31B (free) | |
|---|---|---|
| Vendor | ~anthropic | |
| Quality Score | 100 | 100 |
| Input Price | $1.00/M | Free |
| Output Price | $5.00/M | Free |
| Context Window | 200,000 | 262,144 |
| Max Output | 64,000 | 8,192 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
Who wins by task?
| Task | Anthropic Claude Haiku Latest | Google: Gemma 4 31B (free) |
|---|---|---|
| SQL Generation | 129 | 131 |
| Code Review | 124 | 126 |
| Code Completion | 114 | 129 |
| Code Refactoring | 124 | 127 |
| Bug Fixing | 128 | 130 |
| Unit Test Generation | 120 | 121 |
| Code Documentation | 122 | 126 |
| Regex Writing | 118 | 120 |
| CI/CD Pipelines | 116 | 117 |
| CSV / Spreadsheet Cleanup | 125 | 128 |
| ETL Scripting | 120 | 122 |
| JSON Extraction | 122 | 132 |
| Bulk Data Labeling | 120 | 130 |
| OCR / Document Parsing | 127 | 128 |
| Table Extraction from PDFs | 127 | 128 |
| Long-Document Summarization | 125 | 129 |
| Short-Form Summarization | 114 | 124 |
| Blog Post Writing | 117 | 119 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →
Related comparisons
MoonshotAI: Kimi K2.7 Code vs Anthropic Claude Haiku Latest
MoonshotAI: Kimi K2.7 Code vs Google: Gemma 4 31B (free)
Qwen: Qwen3.7 Plus vs Anthropic Claude Haiku Latest
Qwen: Qwen3.7 Plus vs Google: Gemma 4 31B (free)
MiniMax: MiniMax M3 vs Anthropic Claude Haiku Latest
MiniMax: MiniMax M3 vs Google: Gemma 4 31B (free)
StepFun: Step 3.7 Flash vs Anthropic Claude Haiku Latest
StepFun: Step 3.7 Flash vs Google: Gemma 4 31B (free)