← All models

MiMo-V2.5-Pro

open weights
Xiaomi · released 2026-04-22 · 7 offers

Output 51 tokens/sFirst token 5.5 sContext 1M tokens

Top 3 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
1Novita
2DeepInfra
3DigitalOcean

Composite

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

57.0

includes −9.9 for its Benchmaxxing signal (from 66.9; why, switch off in Options)

dominance-adjusted from 68.5: a better-measured model that is at least as good on each of these inputs ranks above it

Benchmaxxing signal +9.9, medium Benchmaxxing tag · medium report →

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 70AA Intelligence: percentile 82AA Agentic: percentile 60

AA Coding 60.2Coding Agent v1.4 AA Intelligence 26.4AA Agentic 22.7Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

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

Compare this model →

Agentic

  • AA-AnalystAgent4020.0%

    AA-AnalystAgent published 2026-09-10 · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.

  • APEX-Agents-AA72.4%

    APEX-Agents-AA published 2026-09-10 · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.

  • AA-Briefcase44883 Elo

    AA-Briefcase published 2026-09-10 · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

  • GDPval-AA v2631,186 Elo

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

  • Harvey LAB-AA2673.3%

    Harvey LAB-AA published 2026-09-10 · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.

  • ITBench-AA6338.2%

    ITBench-AA published 2026-09-10 · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.

  • Terminal-Bench Hard (AA)9043.2%

    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)6565.2%

    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.

  • τ²-Bench Airline (OpenRouter run)6874.1%

    τ²-Bench Airline (OpenRouter run) published 2026-09-15 · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

  • AA Agentic Index6022.7

    AA Agentic Index published 2026-09-18 · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Coding

  • SciCode (AA subproblems) v1.0.16250.6%

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

  • AA Coding Index7060.2

    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.

Efficiency

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)284.0%

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

  • AA-LCR v1.18879.7%

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

  • MLCR-AA339.4%

    MLCR-AA published 2026-09-10 · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.

Reasoning

Roleplay

  • EQ-Bench 4 v4501,208 Elo

    EQ-Bench 4 v4 · Published board — Measures active emotional and social intelligence of LLMs in multi-turn roleplay chats with simulated personas, ranked by an LLM-judge panel Elo.

Science

Tool-use

  • AutomationBench-AA v1.0.64213.7%

    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)9294.2%

    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) v1.0.1309.9%

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

Unusual results

2 threshold-crossing signals flagged · 27 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 APEX-Agents-AA published 2026-09-10
    Why
    Observed: 0.02434 fraction
    Peer mean 0.22694 · peer sd 0.12479 · n 30 · families 30
    Directed z -1.624 · baseline z 0.418 · gap -2.042 · profile n 26
    0.02434 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: APEX-Agents-AA · published 2026-09-10 · Published board
    Exact value: 0.0243362831858407 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:00f1248e-78e3-4230-8dc8-5e13ba8645e2:apexAgents
  • unusually strong IFBench (AA single-turn) published 2026-09-10
    Why
    Observed: 0.79864 fraction
    Peer mean 0.48006 · peer sd 0.17139 · n 450 · families 331
    Directed z 1.859 · baseline z 0.284 · gap 1.574 · profile n 26
    0.79864 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: IFBench (AA single-turn) · published 2026-09-10 · Published board
    Exact value: 0.798639455782313 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:00f1248e-78e3-4230-8dc8-5e13ba8645e2:ifbench
Missing coverage · 116 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.

Variants / reasoning settings

Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
MiMo-V2.5-Pro60.226.4
MiMo-V2.5-Pro (Non-reasoning)18.3
Token offers by platform · 3 offers (Adjusted $/task)

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

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

OpenRouter (3)

Novita
DigitalOcean
DeepInfra
MiMo-V2.5-Pro — benchmarks & cost | Benchmark Heaven