Anthropic: Claude Haiku Latest vs OpenAI: GPT Mini Latest
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Anthropic: Claude Haiku Latest | OpenAI: GPT Mini Latest | |
|---|---|---|
| Vendor | ~anthropic | ~openai |
| Quality Score | 100 | 100 |
| Input Price | $0.10/M | $0.75/M |
| Output Price | $0.50/M | $4.50/M |
| Context Window | 1,000,000 | 400,000 |
| Max Output | 128,000 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Claude Haiku Latest costs $0.23 and GPT Mini Latest costs $1.88, so Claude Haiku Latest is about 8.3 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 600 pages for GPT Mini Latest.
Across the 10 tasks where they differ, Claude Haiku Latest scores higher on 10 (SQL Generation, Code Completion, Code Documentation and others).
Pick Claude Haiku Latest if you need lower cost, long documents 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 | OpenAI: GPT Mini Latest |
|---|---|---|
| SQL Generation | 133 | 133 |
| Code Completion | 131 | 130 |
| Code Documentation | 131 | 130 |
| Regex Writing | 119 | 119 |
| CSV / Spreadsheet Cleanup | 133 | 133 |
| JSON Extraction | 131 | 130 |
| Bulk Data Labeling | 129 | 128 |
| Long-Document Summarization | 137 | 137 |
| Short-Form Summarization | 123 | 123 |
| Blog Post Writing | 121 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →