Liquid AI model product
73B text model for local agents and specialized applications.
Updated Nov 22, 2026. Default version: LFM3-1.7B
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for LFM3-1.7B.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkIFEval | Score96.66% | Rank01 | Participants72 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score89.10% | Rank01 | Participants27 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWebArena-Verified | Score38.42% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkRULER 128k | Score65.56% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkTAU3-Bench | Score68.01% | Rank04 | Participants9 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkAA-Omniscience Index | Score0.50 points | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkClaw-Eval | Score68.64% | Rank05 | Participants16 | Percentile73.33% | EvidenceC | Evaluated |
| BenchmarkBFCL-V4 | Score71.39% | Rank07 | Participants25 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools, text-only) | Score13.90% | Rank12 | Participants12 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAutomationBench | Score41.29% | Rank16 | Participants33 | Percentile53.13% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score73.03% | Rank26 | Participants48 | Percentile46.81% | EvidenceC | Evaluated |
| BenchmarkAA-LCR | Score52.83% | Rank28 | Participants32 | Percentile12.90% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score28.47% | Rank35 | Participants37 | Percentile5.56% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score73.46% | Rank36 | Participants69 | Percentile48.53% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score32.57% | Rank43 | Participants44 | Percentile2.33% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score23.00% | Rank53 | Participants53 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score12.92% | Rank58 | Participants58 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score7.17% | Rank112 | Participants119 | Percentile5.93% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score43.40% | Rank112 | Participants125 | Percentile10.48% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score63.37% | Rank185 | Participants268 | Percentile31.09% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDliquid/lfm-3-1.7b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.20 | Context262.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for LFM3-1.7B. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLFM3-1.7B | Released | LLMBoard41.51 | Parameters1.7B | ContextN/A | Max outputN/A | Open weightsYes | LicenseLFM Open License v1.0 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about LFM3 1.7B and its available data.
It is the text post-trained checkpoint in the LFM3 family, with a tri-hybrid architecture and a 256K-token context window.
Data as of 2026-11-21.
Common questions about LFM3 1.7B.
LFM3 1.7B's default version was released on Oct 27, 2026.
No official standard PAYG price is currently available for LFM3 1.7B. The lowest tracked third-party offer starts at $0.08 input and $0.20 output via OpenRouter.
LFM3 1.7B was created by Liquid AI.
A context window is not available for the default version.
Yes. The default version is marked as open weight under LFM Open License v1.0.
1 provider offerings are linked to the default version.