PM
Ternary Bonsai 2 27B
Prism ML · Open Weight · rank 113 · bench-align-v5
Self-hostedCanonical idternary-bonsai-2-27b
Access typeOpen Weight
Blended $/1M$0.1875% input / 25% output
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | 9 tok/s | 2026-09-18 | 2026-09-18 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $0.075 | |
| Output / 1M tokens | $0.50 | |
| Cache read / 1M tokens | Unavailable | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $0.18 |
Self-hosted listingPrism ML publishes Ternary Bonsai 2 27B under Apache 2.0 for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs.The rates above are a hosted price matched from another provider, not a first-party list price.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
22 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 85.76 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 85.8 | Graduate-level science questions | Graduate level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| MMLU-Redux MMLU-Redux | 89.09 | Broad academic QA | Advanced general knowledge | Qwen3.6 launch benchmarks |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 (provider run) | 52.8 | Terminal-based software-agent tasks | Professional software engineering | DeepSeek V4 Flash 0731 update |
| BigCodeBench BigCodeBench | 58.1 | Code generation tasks | Software engineering | DeepSeek-V4 Technical Report |
| SWE-bench Verified Software Engineering Benchmark Verified | 60.8 | 500 verified issues | Professional software engineering | SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| LiveCodeBench v6 LiveCodeBench v6 | 90.1 | Fresh programming problems | Competitive programming level | LiveCodeBench official repository and release documentation |
Mathematics
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AIME 2025 American Invitational Mathematics Examination 2025 | 95 | 15 problems | High school olympiad level | American Invitational Mathematics Examination |
| GSM8K Grade School Math 8K | 96.7 | Grade-school math word problems | Grade-school math | DeepSeek-V4 Technical Report |
| MATH-500 MATH-500 Problem Set | 98.8 | 500 problems | High school to undergraduate | Measuring Mathematical Problem Solving With the MATH Dataset |
| AIME26 AIME 2026 | 95.8 | Competition math problems | Olympiad-style mathematics | Qwen3.6 launch benchmarks |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 77.0 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
Instruction Following
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| IFEval Instruction-Following Eval | 91.31 | 541 prompts across 25 instruction types | Instruction precision | Instruction-Following Evaluation for Large Language Models |
| IFBench Instruction Following Benchmark | 74 | — | — | BenchLM |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 (provider run) | 52.8 | Terminal-based software-agent tasks | Professional software engineering | DeepSeek V4 Flash 0731 update |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 80.22 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| BFCL v3 Berkeley Function Calling Leaderboard v3 | 74.9 | Function-calling tasks | Advanced tool use | The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models |
Multimodal & Grounded
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| OCRBench V2 OCRBench V2 | 56.9 | Image OCR tasks | Native visual text understanding | OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning |
| RealWorldQA RealWorldQA | 80.1 | Real-world visual question answering | General visual reasoning | Qwen3.6 launch benchmarks |
| CharXiv (overall) CharXiv Descriptive and Reasoning Combined | 80.0 | Scientific chart description and reasoning | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| A-OKVQA A Benchmark for Visual Question Answering using World Knowledge | 86.8 | Knowledge-grounded visual question answering | Commonsense and world knowledge about images | A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge |
| OmniDocBench 1.6 OmniDocBench v1.6 | 89.1 | Document parsing and extraction | Grounded document reasoning | OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
No lifecycle event references this model.
That is not evidence the model has no lifecycle plan — only that this source published none.
What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-18 22:17 UTC.