Inference
EN
Prism ML

Ternary Bonsai 2 27B

Ternary Bonsai 2 27B is a reasoning model from Prism ML in the Ternary Bonsai 2 family. 13 benchmarks count toward its index, in 7 categories.

  • Open weights
  • Reasoning
  • Input: text · image
  • Released 2026-09
RankedEnough results for an index.
IndexAll categories, out of 100.52.2±5.0Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.21/sMedian 67/s
First tokenSeconds to the first output token.1.5 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.075Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.50Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
prism-ml/ternary-bonsai-2-27b
Max outputMaximum output tokens per request.
33K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.038
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Run locally

26.9B parameters
16-bit
57.5 GB
8-bit
31.0 GB
4-bit
18.1 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 24 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted54.0108 / 218
CodingCode writing and repair.2 counted52.2125 / 209
ReasoningLogic problems and puzzles.1 counted60.1—
MultimodalTasks with images and text.1 counted50.7—
KnowledgeFacts and expert knowledge.2 counted48.6146 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.2 counted52.632 / 63
MathMath problems.3 counted51.181 / 168

Results

13 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH-500 Problem SetMath98.8%1 / 27
LiveCodeBench v6Coding90.1%9 / 59
American Invitational Mathematics Examination 2025Math95.0%9 / 53
AIME 2026Math95.8%8 / 34
Instruction-Following EvalInstruction91.3%23 / 70
Graduate-Level Google-Proof Q&AKnowledge85.8%50 / 141
Artificial Analysis Long Context ReasoningReasoning77.0%82 / 217
τ²-Bench Tool-Agent-User EvaluationAgentic80.2%69 / 149
Instruction Following BenchmarkInstruction74.0%34 / 57
GPQA Diamond · BenchLMKnowledge85.8%56 / 84
RealWorldQAMultimodal80.1%12 / 18
MMLU-ReduxKnowledge89.1%13 / 19
Software Engineering Benchmark VerifiedCoding60.8%85 / 114
Terminal-Bench 2.1 · BenchLMAgentic52.8%72 / 86
Grade School Math 8KMath96.7%—
OmniDocBench v1.6Multimodal89.1%—
A Benchmark for Visual Question Answering using World KnowledgeMultimodal86.8%—
CharXiv Descriptive and Reasoning CombinedMultimodal80.0%—
Berkeley Function Calling Leaderboard v3Agentic74.9%—
BigCodeBenchCoding58.1%—
OCRBench V2Multimodal56.9%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuse

History

5 releases
Index53.0 → 52.2
23 Oct 202612 Nov 2026
Output / 1M$0.50 → $0.50
23 Oct 202612 Nov 2026

Questions

How much does Ternary Bonsai 2 27B cost?
$0.075 per 1M input tokens, $0.50 per 1M output tokens.
How good is Ternary Bonsai 2 27B?
Its index is 52.2 out of 100. That is place 127 of 283 ranked models.
What is Ternary Bonsai 2 27B best at?
Math: 51.1 out of 100, place 81 of 168.
How fast is Ternary Bonsai 2 27B?
21 output tokens per second, 1.5 s to the first token.
What is the context window of Ternary Bonsai 2 27B?
262K tokens.
Is Ternary Bonsai 2 27B open source?
Yes. Its weights are published.
When was Ternary Bonsai 2 27B released?
September 2026.

Badge

Ternary Bonsai 2 27B on Inference360: place 127 of 283, index 52.2
HTML
<a href="https://inference360.ai/models/ternary-bonsai-2-27b"><img src="https://inference360.ai/badges/ternary-bonsai-2-27b.svg" alt="Ternary Bonsai 2 27B on Inference360: place 127 of 283, index 52.2" height="20"></a>
Markdown
[![Ternary Bonsai 2 27B on Inference360: place 127 of 283, index 52.2](https://inference360.ai/badges/ternary-bonsai-2-27b.svg)](https://inference360.ai/models/ternary-bonsai-2-27b)

Compare with

Kimi K2.552.2Solar Pro 452.1Qwen3.6-27B52.1Hy3 Preview52.3dots3-note Preview63.4

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Prism ML

All models
1-bit Bonsai 27BUnrankedTernary Bonsai 27BUnrankedTernary Bonsai 1.7BUnrankedTernary Bonsai 4BUnrankedTernary Bonsai 8BUnranked