# LFM3-1.7B

LiquidAI · Open Weight · rank 199 · bench-align-v5 · Self-hosted

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/lfm3-1-7b  
JSON: https://modelchoice.dev/api/model/lfm3-1-7b

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `lfm3-1-7b` | — |
| Overall score | 31 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 48 | Observed 2026-11-21 · source benchlm:models |
| Context window | 256K tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2026-10-27 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | Unavailable | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models | 59.2 | Observed 2026-11-21 · source benchlm:models |
| Coding | 20.4 | Observed 2026-11-21 · source benchlm:models | 20.3 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 24.6 | Observed 2026-11-21 · source benchlm:models | 24.6 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 60.4 | Observed 2026-11-21 · source benchlm:models | 60.4 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | 72.6 | Observed 2026-11-21 · source benchlm:models | 72.6 | Observed 2026-11-21 · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 15.57 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 193 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Output / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache read / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | Unavailable | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Self-hosted listing.** Liquid AI publishes LFM3-1.7B under the LFM Open License v1.0 for local, on-device and self-hosted use. The October 27, 2026 launch post names the Liquid API, its Playground and OpenRouter as launch channels, but neither it nor Liquid's pricing page (checked October 27, 2026) lists a token price for this checkpoint, so BenchLM represents it as self-host/free-per-token before infrastructure costs. No hosted token rate was published for this model, so its per-token price is unavailable rather than zero.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | Unavailable |
| Modelled tokens | Unavailable |
| Reason | The applicable input rate is unavailable. |

## Benchmark record

28 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 63.37 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 63.4 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HLE (Humanity's Last Exam) | 7.17 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | 0.5 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 7.1 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 12.9 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 43.4 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| LiveCodeBench v6 | 73.5 | Fresh programming problems | Competitive programming level | [LiveCodeBench official repository and release documentation](https://github.com/LiveCodeBench/LiveCodeBench) |
| LiveCodeBench Pro | 31.7 | Quarter-specific contest programming sets | High-end contest programming | [LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?](https://arxiv.org/abs/2506.11928) |
| SWE Multilingual | 23 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| SciCode (Scientific Code Benchmark) | 28.47 | — | — | [BenchLM](https://benchlm.ai/benchmarks/scicode) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 52.8 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| RULER (128K) (RULER at 128K context) | 65.56 | Synthetic long-context tasks | Long-context retrieval and tracing | [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://github.com/NVIDIA/RULER) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFEval (Instruction-Following Eval) | 96.66 | 541 prompts across 25 instruction types | Instruction precision | [Instruction-Following Evaluation for Large Language Models](https://arxiv.org/abs/2311.07911) |
| IFBench (Instruction Following Benchmark) | 73.03 | — | — | [BenchLM](https://benchlm.ai/benchmarks/ifbench) |
| Multi-IF | 89.10 | Multi-turn, multilingual instructions | Keeping constraints across turns and languages | [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://arxiv.org/abs/2410.15553) |
| IFStruct | 93.72 | Structured-output instructions | Exact format and schema compliance | [IFStruct v1.0](https://www.liquid.ai/blog/ifstruct-v1.0) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 12.9 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 13.9 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| MCP Atlas | 32.57 | Tool-integrated agent tasks | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| AutomationBench | 41.3 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| BFCL v4 (Berkeley Function Calling Leaderboard v4) | 71.4 | Function-calling tasks | Advanced tool use | [The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models](https://gorilla.cs.berkeley.edu/leaderboard.html) |
| Claw-Eval | 68.6 | 300 tasks, 2,159 rubrics | Real-world general, multi-turn, and native multimodal agent execution | [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://arxiv.org/abs/2604.06132) |
| τ³-bench results (τ³-Bench Tool-Agent-User Evaluation) | 68.0 | Corrected customer-service tasks plus knowledge and voice evaluation modes | Long-horizon, multimodal, and knowledge-aware tool use | [Official τ³-bench repository and release notes](https://github.com/sierra-research/tau2-bench) |
| WebArena-Verified (WebArena-Verified Browser Agent Benchmark) | 38.42 | 812 verified tasks; separate 258-task Hard subset | Audited stateful browser work | [WebArena-Verified: A Fully Audited Benchmark for Web Agents](https://openreview.net/forum?id=94tlGxmqkN) |
| LiveClaw | 45.60 | Assistant agent tasks | Multi-step assistant work in a real harness | [Introducing LFM3 (Liquid AI)](https://www.liquid.ai/blog/lfm3) |
| EnterpriseOps-Gym (EnterpriseOps-Gym (provider runs)) | 28.20 | Enterprise workflow tasks | Stateful enterprise tool use | [EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings](https://arxiv.org/abs/2603.13594) |
| ToolSandbox | 80.36 | Stateful tool-use conversations | Tool use with changing state | [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://github.com/apple-aiml-research/ToolSandbox) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

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 claim

Values 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. Last attempted fetch for this model's score: 2026-11-21 05:17 UTC.
