← All models

Mistral Small 3.2

open weightsdeprecated by benchmark source
Mistral · released 2025-06-20 · 5 offers

Context 128K tokens

Top 5 cheapest providers (Adjusted $/task)

The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Parasail
2DeepInfra
3Venice
4IONOS
5Scaleway

Composite

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

9.3

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 12AA Intelligence: percentile 24

AA Coding 12.5Coding Agent v1.4 AA Intelligence 7.0AA Agentic Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

25 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Agentic

  • GDPval-AA v2529 Elo

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

  • Terminal-Bench Hard (AA)376.8%

    Terminal-Bench Hard (AA) pinned revision 74221fb · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)135.6%

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

  • Terminal-Bench v4.0 (AA)180.0%

    Terminal-Bench v4.0 (AA) v4.0 · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

Coding

  • SciCode (AA subproblems) v1.0.1828.6%

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

  • AA Coding Index1212.5

    AA Coding Index published 2026-09-19 · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Instruction-following

  • IFBench (AA single-turn)2333.5%

    IFBench (AA single-turn) published 2026-09-10 · Published board — Tests precise single-turn instructions with deterministic rule checks.

  • LisanBench word chains, v0.2.0 (Lisan al Gaib)1252.7

    LisanBench word chains, v0.2.0 (Lisan al Gaib) v0.2.0 · Published board — A model builds the longest chain of English words it can, each differing from the last by one letter, with no repeats and only dictionary words, from 50 starting words; any broken rule ends the chain.

Knowledge

Long-context

  • GDP.pdf (AA)10.0%

    GDP.pdf (AA) published 2026-09-10 · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.12420.3%

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

Math

  • AIME 2025 (AA) v20252927.0%

    AIME 2025 (AA) v2025 · Published board — Advanced mathematical problem solving on AIME I and II 2025.

Reasoning

Science

Tool-use

  • AutomationBench-AA v1.0.670.3%

    AutomationBench-AA v1.0.6 · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

  • τ²-Bench Telecom (AA)3729.5%

    τ²-Bench Telecom (AA) published 2026-09-10 · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.

  • τ³-Banking (AA) v1.0.1176.2%

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

Uncensored

  • UGI Willingness926.50

    UGI Willingness published 2026-09-10 · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.

  • UGI7740.4

    UGI published 2026-09-10 · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.

Vision

Writing

  • EQ-Bench Creative Writing v3351,253 Elo

    EQ-Bench Creative Writing v3 v3 · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.

  • EQ-Bench Longform Creative Writing v1.112441.6

    EQ-Bench Longform Creative Writing v1.11 · Published board — LLM-judged benchmark in which models plan and write a short story/novella over 8x 1000-word turns, scored 0-100 across 14 rubric dimensions.

  • Slop Score10052.7

    Slop Score published 2026-09-10 · Published board — Leaderboard and analysis tool scoring how much model writing resembles AI slop via overused words, contrast patterns, and trigrams.

  • UGI Writing7036.3

    UGI Writing published 2026-09-10 · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.

Unusual results

1 threshold-crossing signal flagged · 25 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.

Missing coverage · 118 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 · 5 offers (Adjusted $/task)

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

5 offers within the active global filters; “—” means the catalog is active but no public token price is available.

OpenRouter (3)

Parasail
DeepInfra
Venice

IONOS (1)

IONOS

Scaleway (1)

Scaleway
Mistral Small 3.2 — benchmarks & cost | Benchmark Heaven