# Ternary Bonsai 2 27B vs Ultramarine 1 Flash

> Side-by-side benchmark comparison for Ternary Bonsai 2 27B and Ultramarine 1 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/ternary-bonsai-2-27b-vs-ultramarine-1-flash
- Last updated: October 15, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Ternary Bonsai 2 27B and Ultramarine 1 Flash share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Ternary Bonsai 2 27B has the lower published output-token price.
- Ternary Bonsai 2 27B has the larger published context window at 262K.

## Model Snapshot

| Property | Ternary Bonsai 2 27B | Ultramarine 1 Flash |
|----------|----------|----------|
| Creator | Prism ML | Paper Instruments |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | Not disclosed |
| Independent public score (not head-to-head) | 53.85 | null |
| Benchmarks Covered | 21 | 5 |
| Pricing (input/output) | $0.00 / $0.00 | $0.15 / $0.50 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: Coming soon
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| τ²-bench results | 80.2% | Coming soon | Coming soon |
| BFCL v3 | 74.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 52.8% | 83.2% | Ultramarine 1 Flash |
| JobBench | Coming soon | 62.9% | Coming soon |
| AutomationBench | Coming soon | 50.2% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: Coming soon
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 90.1% | Coming soon | Coming soon |
| BigCodeBench | 58.1% | Coming soon | Coming soon |
| SWE-bench Verified | 60.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 52.8% | 83.2% | Ultramarine 1 Flash |
| DeepSWE | Coming soon | 61.5% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: 78.8 (Unranked · 1 rankable row)
- Ultramarine 1 Flash public-lane score: Coming soon

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: Coming soon
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| CharXiv (overall) | 80.0% | Coming soon | Coming soon |
| A-OKVQA | 86.8% | Coming soon | Coming soon |
| OmniDocBench 1.6 | 89.1% | Coming soon | Coming soon |
| RealWorldQA | 80.1% | Coming soon | Coming soon |
| OCRBench V2 | 56.9% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: Coming soon
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Redux | 89.1% | Coming soon | Coming soon |
| GPQA | 85.8% | Coming soon | Coming soon |
| GPQA-D | 85.8% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: 74 (#67/146)
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 91.3% | Coming soon | Coming soon |
| IFBench | 74% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Ternary Bonsai 2 27B public-lane score: 86.2 (Unranked · 4 rankable rows)
- Ultramarine 1 Flash public-lane score: Coming soon

| Benchmark | Ternary Bonsai 2 27B | Ultramarine 1 Flash | Winner |
|-----------|-----------|-----------|--------|
| GSM8K | 96.7% | Coming soon | Coming soon |
| MATH-500 | 98.8% | Coming soon | Coming soon |
| AIME 2025 | 95% | Coming soon | Coming soon |
| AIME26 | 95.8% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Ternary Bonsai 2 27B and Ultramarine 1 Flash?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Ternary Bonsai 2 27B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-ternary-bonsai-2-27b)
- [Ultramarine 1 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-ultramarine-1-flash)
- [Ternary Bonsai 2 27B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-ternary-bonsai-2-27b)
- [Ultramarine 1 Flash vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-ultramarine-1-flash)

## Explore More

- [Ternary Bonsai 2 27B profile](/models/ternary-bonsai-2-27b)
- [Ultramarine 1 Flash profile](/models/ultramarine-1-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)