Anthropic: Claude Haiku 5.5 vs PrismML: Ternary Bonsai 2 27B
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-10-08.
| Anthropic: Claude Haiku 5.5 | PrismML: Ternary Bonsai 2 27B | |
|---|---|---|
| Vendor | anthropic | prism-ml |
| Quality Score | 100 | 100 |
| Benchmark Score | 73.6 | - |
| Input Price | $0.10/M | $0.07/M |
| Output Price | $0.50/M | $0.50/M |
| Context Window | 1,000,000 | 262,144 |
| Max Output | 128,000 | 32,768 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 71.6 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Ternary Bonsai 2 27B costs $0.20 and Claude Haiku 5.5 costs $0.23, so Ternary Bonsai 2 27B is slightly cheaper for the same work.
Claude Haiku 5.5 reads up to 1,000,000 tokens at once, roughly 1,500 pages of text, against about 393 pages for Ternary Bonsai 2 27B.
Across the 18 tasks where they differ, Claude Haiku 5.5 scores higher on 18 (SQL Generation, Code Review, Code Completion and others).
Claude Haiku 5.5 was released in October 2026 and Ternary Bonsai 2 27B in September 2026.
Pick Claude Haiku 5.5 if you need long documents or the stronger all-round task scores; pick Ternary Bonsai 2 27B if you need lower cost.
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 5.5 | PrismML: Ternary Bonsai 2 27B |
|---|---|---|
| SQL Generation | 142 | 131 |
| Code Review | 145 | 126 |
| Code Completion | 133 | 129 |
| Code Refactoring | 147 | 127 |
| Bug Fixing | 149 | 130 |
| Unit Test Generation | 132 | 121 |
| Code Documentation | 138 | 126 |
| Regex Writing | 127 | 119 |
| CI/CD Pipelines | 128 | 117 |
| Frontend Component Design | 130 | 122 |
| Data Analysis | 134 | 124 |
| CSV / Spreadsheet Cleanup | 136 | 128 |
| ETL Scripting | 138 | 122 |
| OCR / Document Parsing | 134 | 128 |
| Table Extraction from PDFs | 134 | 128 |
| Long-Document Summarization | 149 | 129 |
| Short-Form Summarization | 127 | 123 |
| Blog Post Writing | 130 | 119 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →