Anthropic: Claude Haiku Latest vs Qwen: Qwen3.6 35B A3B
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Anthropic: Claude Haiku Latest | Qwen: Qwen3.6 35B A3B | |
|---|---|---|
| Vendor | ~anthropic | qwen |
| Quality Score | 100 | 100 |
| Benchmark Score | - | 52.9 |
| Input Price | $0.10/M | $0.10/M |
| Output Price | $0.50/M | $0.90/M |
| Context Window | 1,000,000 | 262,144 |
| Max Output | 128,000 | 235,929 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | - | 52.2 |
| ai_index_agentic | - | 35.3 |
| ai_index_coding | - | 69.1 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Claude Haiku Latest costs $0.23 and Qwen3.6 35B A3B costs $0.33, so Claude Haiku Latest is about 1.4 times cheaper for the same work.
Claude Haiku Latest reads up to 1,000,000 tokens at once, roughly 1,500 pages of text, against about 393 pages for Qwen3.6 35B A3B.
Only Qwen3.6 35B A3B offers video input.
Across the 20 tasks where they differ, Claude Haiku Latest scores higher on 1 (Code Completion), Qwen3.6 35B A3B on 19 (SQL Generation, Code Review, Code Refactoring and others).
Pick Claude Haiku Latest if you need lower cost or long documents; pick Qwen3.6 35B A3B if you need video input 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 Haiku Latest | Qwen: Qwen3.6 35B A3B |
|---|---|---|
| SQL Generation | 133 | 154 |
| Code Review | 132 | 147 |
| Code Completion | 131 | 130 |
| Code Refactoring | 136 | 144 |
| Bug Fixing | 136 | 156 |
| Unit Test Generation | 124 | 140 |
| Code Documentation | 131 | 133 |
| Regex Writing | 119 | 129 |
| CI/CD Pipelines | 120 | 132 |
| Frontend Component Design | 122 | 137 |
| Data Analysis | 124 | 151 |
| CSV / Spreadsheet Cleanup | 133 | 141 |
| ETL Scripting | 128 | 138 |
| JSON Extraction | 131 | 143 |
| Bulk Data Labeling | 129 | 133 |
| OCR / Document Parsing | 131 | 138 |
| Table Extraction from PDFs | 131 | 138 |
| Long-Document Summarization | 137 | 142 |
| Short-Form Summarization | 123 | 128 |
| Blog Post Writing | 121 | 130 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →