← All models

GLM-5.2 (max)

open weightsdeprecated by benchmark source
Z.ai · released 2026-06-16 · 39 offers

Output 72 tokens/sFirst token 8.6 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
1DeepInfra
2Novita
3DigitalOcean
4CoreWeave
5Chutes

Composite

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

76.5

includes −0.0 for its Benchmaxxing signal (from 76.5; why, switch off in Options)

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 78Coding Agent v1.4: percentile 23AA Intelligence: percentile 90AA Agentic: percentile 77Epoch ECI: percentile 58Software ECI: percentile 50DesignArena: percentile 58

AA Coding 68.8Coding Agent v1.4 43.3AA Intelligence 34.0AA Agentic 39.4Epoch ECI 151.9Software ECI 152.3DesignArena 1236/1251

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

Benchmark sheet

41 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

  • APEX-Agents-AA8333.7%

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

  • AA-Briefcase681,234 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 v2801,418 Elo

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

  • Harvey LAB-AA7491.0%

    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-AA8442.7%

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

  • Terminal-Bench Hard (AA)9550.8%

    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)7777.9%

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

  • ApprenticeBench API (NeoCognition)1517.0%

    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.

  • Terminal-Bench 2.1 (Vals Index v2)3567.8%

    Terminal-Bench 2.1 (Vals Index v2) v2 · Published board — Command-line interface problem solving, as run by Vals AI.

  • HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)597.1%

    HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.

  • τ²-Bench Airline (OpenRouter run)7274.9%

    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.)

  • EBR-bench (Earthborne Rangers, Epoch AI)129.5%

    EBR-bench (Earthborne Rangers, Epoch AI) published 2026-09-18 · Published board — Learning-capability test: models repeatedly play the obscure campaign board game Earthborne Rangers with note-taking, and the score measures whether results improve across playthroughs.

  • PostTrainBench v1.1031.7%

    PostTrainBench v1.1 · Claude Code — Agents retrain four small base models (gemma-3-4b-pt, SmolLM3-3B-Base, Qwen3-1.7B-Base, Qwen3-4B-Base) for each of 7 benchmark families; the leaderboard value is the weighted mean over base models × benchmarks, aggregated over the 2–3 listed runs per agent.

  • AA Agentic Index7739.4

    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

Efficiency

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)4610.4%

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

  • AA-LCR v1.18578.3%

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

  • MLCR-AA267.2%

    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)3359.2%

    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)3829.3%

    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)4621.0%

    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.

  • AA Intelligence Index9034.0

    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 v1.0.65428.4%

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

  • EnterpriseOps-Gym-AA6242.7%

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

  • τ²-Bench Telecom (AA)10099.1%

    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) v1.0.17634.6%

    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 · 40 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: 0.20857 fraction
    Peer mean 0.03928 · peer sd 0.07596 · n 522 · families 369
    Directed z 2.229 · baseline z 0.487 · gap 1.742 · profile n 39
    0.20857 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: CritPt (AA) · published 2026-09-10 · Published board
    Exact value: 0.208571428571429 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:critpt
Missing coverage · 100 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
GLM-5.2 (max)68.834.0
GLM-5.2 (Non-reasoning)46.522.4
Token offers by platform · 28 offers (Adjusted $/task)

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

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

OpenRouter (19)

DecartfreeFree route: rate- and quota-limited, availability may change — not used as a paid pricenot a paid price
DeepInfra
Novita
DigitalOcean
CoreWeave
Phala
Inceptron
SiliconFlow
BaseTen
Fireworks
Together
Wafer
Venice
Parasail
Z.AI
BaseTen
Fireworks
Fireworks
Decart

Chutes (1)

Chutes

Inceptron (1)

Inceptron

T-Systems LLM Hub (1)

T-Systems LLM Hub

TensorX (1)

TensorX

TrustedTokens (1)

TrustedTokens

Google Vertex AI (1)

Google Vertex AI

Nebius (1)

Nebius

Azure AI Foundry (1)

Azure AI Foundry

Scaleway (1)

Scaleway
GLM-5.2 (max) — benchmarks & cost | Benchmark Heaven