Anthropic: Claude Sonnet 5 vs Anthropic: Claude Sonnet 5 (batch)
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Anthropic: Claude Sonnet 5 | Anthropic: Claude Sonnet 5 (batch) | |
|---|---|---|
| Vendor | anthropic | anthropic |
| Quality Score | 100 | 100 |
| Benchmark Score | 91.4 | 91.4 |
| Input Price | $2.00/M | $1.00/M |
| Output Price | $10.00/M | $5.00/M |
| Context Window | 1,000,000 | 1,000,000 |
| Max Output | 128,000 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 88.0 | 88.0 |
| ai_index_agentic | 77.0 | 77.0 |
| ai_index_coding | 100.0 | 100.0 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Claude Sonnet 5 (batch) costs $2.25 and Claude Sonnet 5 costs $4.50, so Claude Sonnet 5 (batch) is about 2.0 times cheaper for the same work.
Both read up to 1,000,000 tokens at once, roughly 1,500 pages of text.
Across the 10 tasks where they differ, Claude Sonnet 5 (batch) on 10 (SQL Generation, Code Completion, Code Documentation and others).
Pick Claude Sonnet 5 (batch) if you need lower cost 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 | Anthropic: Claude Sonnet 5 | Anthropic: Claude Sonnet 5 (batch) |
|---|---|---|
| SQL Generation | 171 | 171 |
| Code Completion | 119 | 120 |
| Code Documentation | 141 | 143 |
| Regex Writing | 135 | 136 |
| CSV / Spreadsheet Cleanup | 153 | 154 |
| JSON Extraction | 138 | 140 |
| Bulk Data Labeling | 124 | 126 |
| Long-Document Summarization | 159 | 160 |
| Short-Form Summarization | 122 | 123 |
| Blog Post Writing | 140 | 140 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →