RadixArk: DaisyRose 27B vs PrismML: Ternary Bonsai 2 9B
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-21.
| RadixArk: DaisyRose 27B | PrismML: Ternary Bonsai 2 9B | |
|---|---|---|
| Vendor | radixark | prism-ml |
| Quality Score | 100 | 100 |
| Input Price | $0.15/M | $0.08/M |
| Output Price | $1.88/M | $0.13/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 235,929 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Ternary Bonsai 2 9B costs $0.11 and DaisyRose 27B costs $0.62, so Ternary Bonsai 2 9B is about 5.5 times cheaper for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
Across the 10 tasks where they differ, Ternary Bonsai 2 9B on 10 (SQL Generation, Code Completion, Code Documentation and others).
DaisyRose 27B was released in November 2026 and Ternary Bonsai 2 9B in October 2026.
Pick Ternary Bonsai 2 9B 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 | RadixArk: DaisyRose 27B | PrismML: Ternary Bonsai 2 9B |
|---|---|---|
| SQL Generation | 131 | 131 |
| Code Completion | 128 | 129 |
| Code Documentation | 126 | 126 |
| Regex Writing | 119 | 120 |
| CSV / Spreadsheet Cleanup | 128 | 128 |
| JSON Extraction | 131 | 132 |
| Bulk Data Labeling | 129 | 129 |
| Long-Document Summarization | 129 | 129 |
| Short-Form Summarization | 123 | 124 |
| Blog Post Writing | 119 | 119 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →