head-to-head

Anthropic: Claude Haiku 5.5 vs PrismML: Ternary Bonsai 2 27B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-22.

Anthropic: Claude Haiku 5.5 PrismML: Ternary Bonsai 2 27B
Vendoranthropicprism-ml
Quality Score100100
Input Price$0.10/M$0.07/M
Output Price$0.50/M$0.50/M
Context Window1,000,000262,144
Max Output128,00032,768
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 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 14 tasks where they differ, Claude Haiku 5.5 scores higher on 14 (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?

TaskAnthropic: Claude Haiku 5.5PrismML: Ternary Bonsai 2 27B
SQL Generation 133 131
Code Review 132 126
Code Completion 131 129
Code Refactoring 136 127
Bug Fixing 136 130
Unit Test Generation 124 121
Code Documentation 131 126
CI/CD Pipelines 120 117
CSV / Spreadsheet Cleanup 133 128
ETL Scripting 128 122
OCR / Document Parsing 131 128
Table Extraction from PDFs 131 128
Long-Document Summarization 137 129
Blog Post Writing 121 119

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Thinking Machines: Inkling 2 Mini vs Anthropic: Claude Haiku 5.5 RadixArk: DaisyRose 27B vs Anthropic: Claude Haiku 5.5 Google: Gemini 4 Neon vs Anthropic: Claude Haiku 5.5 Google: Gemini 4 Neon (batch) vs Anthropic: Claude Haiku 5.5 OpenAI: GPT-6.2 Sol Pro vs Anthropic: Claude Haiku 5.5 OpenAI: GPT-6.2 Sol Pro (batch) vs Anthropic: Claude Haiku 5.5 OpenAI: GPT-6.2 Sol vs Anthropic: Claude Haiku 5.5 OpenAI: GPT-6.2 Sol (batch) vs Anthropic: Claude Haiku 5.5

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.