← All models

LFM2.5-2.6B

open weights
Liquid AI · released 2026-08-04 · 2 offers

Context 128K tokens

Providers

A price exists, but your data filter hides it.

Liquid is not on OpenRouter's list of providers that neither train on nor retain prompts, and such providers are left out while “Trains or keeps your data” is off.

Composite

2 of 7 inputs6 radar axes: DesignArena's two boards share one

5.9

 Thin data · 2/7Based on only 2 of 7 Composite inputs — treat this rank as uncertain
AA Coding v4.xCoding Agent v1.4AA Intelligence (est.)AA AgenticEpoch ECISoftware ECIDesignArenaAA Coding v4.x: percentile 6AA Intelligence (est.): percentile 32

AA Coding v4.x 7.7Coding Agent v1.4 —AA Intelligence (est.) 3.7AA Agentic —Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

9 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Agentic

  • GDPval-AA v211202 Elo

    GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench v2.1 (AA)114.5%

    Terminal-Bench v2.1 (AA) v2.1 → · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

Coding

  • SciCode (AA subproblems) v1.0.1014.4%

    SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.

  • AA Coding Index v4.x · frozen 2026-10-2767.70

    AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).

Knowledge

Long-context

  • AA-LCR v1.1135.7%

    AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

Science

Tool-use

  • τ³-Banking (AA) v1.0.1217.2%

    τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Unusual results

1 threshold-crossing signal flagged · 10 eligible benchmark families

How flags are calculated

Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.

  • unusually weak SciCode (AA subproblems) v1.0.1
    Why
    Observed: 0.14352 fraction
    Peer mean 0.46304 · peer sd 0.10542 · n 183 · families 125
    Directed z -3.031 · baseline z -0.887 · gap -2.144 · profile n 9
    0.14352 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗
    Evidence
    Axis: SciCode (AA subproblems) · v1.0.1 · Published board
    Exact value: 0.143518518518519 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:e1bfc488-5f48-4d42-abf6-7f3c53d79f9c:scicode
Missing coverage · 310 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Token offers by platform · 0 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

0 offers within the active global filters, 2 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.

All 2 offers of this model are outside the active global filters.

LFM2.5-2.6B — benchmarks & cost | Benchmark Heaven