← All models

Kimi K3 (max)

open weights★ featured
Moonshot AI · released 2026-07-16 · 25 offers

Output 38 tokens/sFirst token 3.6 sContext 1M 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
1Relace
2Sail Research
3Together
4DigitalOcean
5Morph

Composite

6 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one

91.7

includes −1.6 for its Benchmaxxing signal (from 93.3; why, switch off in Options)

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 93AA Intelligence: percentile 96AA Agentic: percentile 92Epoch ECI: percentile 81Software ECI: percentile 87DesignArena: percentile 88

AA Coding 76.2Coding Agent v1.4 AA Intelligence 43.8AA Agentic 50.6Epoch ECI 157.6Software ECI 161.5DesignArena 1309/1332

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

Benchmark sheet

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

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • Software ECI · attached
  • DesignArena Web Apps (agentic) · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • AA-AnalystAgent5838.8%

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

  • APEX-Agents-AA9741.3%

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

  • AA-Briefcase901,497 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 v2921,584 Elo

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

  • Harvey LAB-AA9894.6%

    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-AA9447.7%

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

  • Terminal-Bench v2.1 (AA)9085.0%

    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)7312.6%

    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.

  • ApprenticeBench CUA (NeoCognition)3118.0%

    ApprenticeBench CUA (NeoCognition) published 2026-09-14 · Claude Code — A computer-use agent operates the Odoo ERP through its screens across 100 sequential accounts-payable tasks with diminishing mentoring.

  • ApprenticeBench API (NeoCognition)4625.0%

    ApprenticeBench API (NeoCognition) published 2026-09-14 · Claude Code — An agent completes the same 100 sequential accounts-payable tasks in the Odoo ERP with diminishing mentoring, using dedicated application API calls instead of the screen interface.

  • τ²-Bench Airline (OpenRouter run)5270.9%

    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 Index9250.6

    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) v1.0.19759.5%

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

  • Code Migration (Vals Index v2 subset)1916.0%

    Code Migration (Vals Index v2 subset) v2 · Published board — Porting projects to another language, including COBOL modernization.

  • DeepSWE (Datacurve, via Epoch AI)7168.5%

    DeepSWE (Datacurve, via Epoch AI) published 2026-09-15 · mini-swe-agent — Pass rate of coding agents on original, long-horizon software engineering tasks, run by Datacurve with the mini-swe-agent harness.

  • FrontierSWE v25725.9%

    FrontierSWE v2 v2 · proximus — 34 hand-written real-world software tasks: each model attempts every task in its own CLI agent harness for 5 trials per task under a 20-hour budget, scored by the site’s own review protocol; the headline value is mean@5 in percent with best@5/worst@5 bounds.

  • AA Coding Index9376.2

    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.

  • DesignArena Web Apps (agentic)891,309 Elo

    DesignArena Web Apps (agentic) published 2026-09-19 · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

  • DesignArena Full-Stack961,332 Elo

    DesignArena Full-Stack published 2026-09-19 · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

Efficiency

Instruction-following

  • LisanBench word chains, v0.2.0 (Lisan al Gaib)9610,521

    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)8322.0%

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

  • AA-LCR v1.110088.7%

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

  • MLCR-AA8638.3%

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

Math

  • FrontierMath Tiers 1–3 v2 (Epoch AI)7072.2%

    FrontierMath Tiers 1–3 v2 (Epoch AI) v2 · Published board — Unpublished, expert-written mathematics problems from undergraduate to research level with automatically checkable answers, run by Epoch AI on its private v2 set.

  • FrontierMath Tier 4 v2 (Epoch AI)5639.0%

    FrontierMath Tier 4 v2 (Epoch AI) v2 · Published board — The hardest, research-level tier of Epoch AI's unpublished FrontierMath problems, run by Epoch AI on its private v2 set.

Reasoning

  • Chess Puzzles (Epoch AI)7239.0%

    Chess Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.

  • Mystery Game Puzzles (Epoch AI)3926.0%

    Mystery Game Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.

  • AA Intelligence Index9643.8

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

Science

Tool-use

  • AutomationBench-AA v1.0.68958.3%

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

  • EnterpriseOps-Gym-AA7945.3%

    EnterpriseOps-Gym-AA published 2026-09-10 · Published board — Tests enterprise workflows through MCP tools against resettable application environments.

  • τ³-Banking (AA) v1.0.19546.0%

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

  • Excel Modeling Benchmark (Vals Index v2)6966.4%

    Excel Modeling Benchmark (Vals Index v2) v2 · Published board — Building and editing financial models in spreadsheets.

Vision

Unusual results

1 threshold-crossing signal flagged · 38 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 strong CritPt (AA) published 2026-09-10
    Why
    Observed: 0.23429 fraction
    Peer mean 0.03928 · peer sd 0.07596 · n 522 · families 369
    Directed z 2.567 · baseline z 0.934 · gap 1.634 · profile n 37
    0.23429 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: CritPt (AA) · published 2026-09-10 · Published board
    Exact value: 0.234285714285714 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:f7d2fc3e-1f7b-405f-818c-07952a4af78f:critpt
Missing coverage · 101 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
Kimi K3 (max)76.243.8
Kimi K3 (low)72.030.5
Kimi K3

SUBSCRIPTION PLAN

GitHub Copilot

Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.

Input $3.00 / 1M
Cached input $0.300 / 1M
Output $15.00 / 1M
Status GA
Token offers by platform · 24 offers (Adjusted $/task)

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

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

OpenRouter (19)

Relace
Sail Research
Together
DigitalOcean
Morph
Moonshot AI
Modal
Fireworks
Phala
InferenceNet
Wafer
BaseTen
Makora
DeepInfra
Fireworks
Parasail
Morph
Chutes
Fireworks

Chutes (1)

Chutes

TensorX (1)

TensorX

Nebius (1)

Nebius

Azure AI Foundry (2)

Azure AI Foundry
Azure AI Foundry
Kimi K3 (max) — benchmarks & cost | Benchmark Heaven