← All models

LFM2.5-2.6B

open weights
Liquid AI · released 2026-08-04 · 0 offers

Context 128K tokens

Providers

No provider publishes an API price for this model yet, so no cost can be modeled.

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 320 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 · 311 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.

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