Benchmark Heaven
Price & provider filters · adjusted costs
Global
Applies to price views & model offers; benchmark evidence stays unfiltered
← All models

GLM-5.2 (max)

open weights★ featured
Z.ai · released 2026-06-16 · 39 recorded token offers

Top 5 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderPlatformRaw input $/1MRaw output $/1MAdjusted $/task
1DeepInfraOpenRouter$0.487$1.56
2AmbientOpenRouter$0.600$2.00
3NovitaOpenRouter$0.683$2.15
4DigitalOceanOpenRouter$0.700$2.20
5CoreWeaveOpenRouter$0.760$2.42

Benchmarks

Composite70.9
Mean-imputed base68.3
Dominance adjustment+2.6
Composite evidence5/5
AA Coding · unversioned snapshot 2026-09-1068.8
AA Coding Agent · v1.4 · 2026-09-0943.3
AA Intelligence · unversioned snapshot 2026-09-1038.6
DesignArena Frontend · unversioned snapshot 2026-09-101242
DesignArena Full-Stack · unversioned snapshot 2026-09-101248
Output speed (t/s)70

Intelligence.ai (formerly DesignArena) publishes this result at product/family scope without an effort setting. It is attached exactly once to glm-5.2::max, the deterministic family representative used by collapsed comparisons; this does not assert that Intelligence.ai tested this specific effort setting.

MODEL EVIDENCE

Benchmark sheet

20 / 73 registered benchmark versions covered · 24 observations including existing index snapshots.

Compare this model ↗
Composite retains Coding Agent v1.4 · source 2026-09-09

The five Composite inputs remain unchanged. Its Coding Agent input is the median across complete harness results in the retained v1.4 snapshot from 2026-09-09. Artificial Analysis now publishes v1.5, with different components. Explore current v1.5 separately. Dated snapshot labels on other indices identify unversioned source captures, not a verified semantic version.

Profile signals

No threshold-crossing signal · 24 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.

Protocol-compatible measured/vendor divergences

No verified protocol-compatible vendor/measured pair is available for this model; agreement cannot be assessed.

Agentic

Agentic: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
APEX-Agents-AA

Version snapshot-2026-09-10

Published board

Tests professional-service tasks that require agents to produce locally graded deliverables.

0.33702 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: APEX-Agents-AA · snapshot-2026-09-10 · Published board
Exact value: 0.337020648967552 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:apexAgents
AA-Briefcase

Version snapshot-2026-09-10

Published board

Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

1233.94 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Briefcase · snapshot-2026-09-10 · Published board
Exact value: 1233.94 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:briefcaseBreakdown.overall.elo
GDPval-AA v2

Version 2

Published board

Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

1417.62 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDPval-AA v2 · 2 · Published board
Exact value: 1417.62 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:gdpval
Harvey LAB-AA

Version snapshot-2026-09-10

Published board

Tests legal-work deliverables across practice areas on Harvey's private task set.

0.90968 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Harvey LAB-AA · snapshot-2026-09-10 · Published board
Exact value: 0.909683022145028 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:harveyLab
ITBench-AA

Version snapshot-2026-09-10

Published board

Tests root-cause diagnosis from offline Kubernetes incident snapshots.

0.42655 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: ITBench-AA · snapshot-2026-09-10 · Published board
Exact value: 0.426553672316384 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:itBenchSre
Terminal-Bench Hard (AA)

Version 74221fb

Published board

Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

0.50758 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench Hard (AA) · 74221fb · Published board
Exact value: 0.507575757575758 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:terminalbenchHard
Terminal-Bench v2.1 (AA)

Version 2.1

Published board

Tests terminal-based work on the 89-task verified refresh using Terminus 2.

0.77903 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v2.1 (AA) · 2.1 · Published board
Exact value: 0.779026217228464 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:terminalbenchV21

Coding

Coding: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
SciCode (AA subproblems)

Version 1.0.1

Published board

Tests scientific Python programming with scientist-annotated background information.

0.51157 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: SciCode (AA subproblems) · 1.0.1 · Published board
Exact value: 0.511574074074074 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:scicode
AA Coding Index

Version snapshot-2026-09-10 (unversioned)

Published board

Published AA index from the retained API snapshot. No verified semantic version was supplied.

68.8 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Coding Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 68.8 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_coding_index:glm-5.2::max
Protocol: inspect · file data/raw/artificialanalysis.json
DesignArena Frontend

Version snapshot-2026-09-10 (unversioned)

Published board

Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

1242 Elomeasured5940 battlesobserved 2026-09-10designarena.ai
Evidence
Axis: DesignArena Frontend · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 1242 Elo
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:frontend:glm-5.2::max
Protocol: inspect · file data/raw/designarena.json
DesignArena Full-Stack

Version snapshot-2026-09-10 (unversioned)

Published board

Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

1248 Elomeasured2525 battlesobserved 2026-09-10designarena.ai
Evidence
Axis: DesignArena Full-Stack · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 1248 Elo
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:fullstack:glm-5.2::max
Protocol: inspect · file data/raw/designarena.json

Instruction-following

Instruction-following: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
IFBench (AA single-turn)

Version snapshot-2026-09-10

Published board

Tests precise single-turn instructions with deterministic rule checks.

0.73333 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: IFBench (AA single-turn) · snapshot-2026-09-10 · Published board
Exact value: 0.733333333333333 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:ifbench

Knowledge

Knowledge: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
Humanity's Last Exam (AA text-only)

Version snapshot-2026-09-10

Published board

Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.

0.41149 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Humanity's Last Exam (AA text-only) · snapshot-2026-09-10 · Published board
Exact value: 0.411492122335496 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:hle
AA-Omniscience Index

Version snapshot-2026-09-10

Published board

Tests factual reliability while rewarding correct answers and penalizing hallucinations.

4.43333 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Omniscience Index · snapshot-2026-09-10 · Published board
Exact value: 4.43333333333333 points
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:omniscience

Long-context

Long-context: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
GDP.pdf (AA)

Version snapshot-2026-09-10

Published board

Tests professional reasoning over long PDFs with AA document preparation and grading.

0.104 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDP.pdf (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.104 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:gdpPdfAllPass
AA-LCR v1.1

Version 1.1

Published board

Tests reasoning across multiple long documents with corrected answer keys and grading.

0.78333 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-LCR v1.1 · 1.1 · Published board
Exact value: 0.783333333333333 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:lcr
MLCR-AA

Version snapshot-2026-09-10

Published board

Tests medical-record synthesis and reasoning across long, fragmented case documents.

0.07222 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: MLCR-AA · snapshot-2026-09-10 · Published board
Exact value: 0.0722222222222222 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:mlcrOverall

Reasoning

Reasoning: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
AA Intelligence Index

Version snapshot-2026-09-10 (unversioned)

Published board

Published AA index from the retained API snapshot. No verified semantic version was supplied.

38.6 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Intelligence Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 38.6 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_intelligence_index:glm-5.2::max
Protocol: inspect · file data/raw/artificialanalysis.json

Science

Science: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
CritPt (AA)

Version snapshot-2026-09-10

Published board

Tests research-level physics reasoning with Python, symbolic and numerical answers.

0.20857 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: CritPt (AA) · snapshot-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
GPQA Diamond (AA)

Version snapshot-2026-09-10

Published board

Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

0.89495 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GPQA Diamond (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.894949494949495 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:gpqa

Tool-use

Tool-use: every observation for this exact model configuration
Benchmark / versionEvaluation groupScore / provenance
AutomationBench-AA

Version 1.0.6

Published board

Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

0.28399 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AutomationBench-AA · 1.0.6 · Published board
Exact value: 0.2839897721005435 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:automationBenchPartialScore
EnterpriseOps-Gym-AA

Version snapshot-2026-09-10

Published board

Tests enterprise workflows through MCP tools against resettable application environments.

0.42734 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: EnterpriseOps-Gym-AA · snapshot-2026-09-10 · Published board
Exact value: 0.42733512384362876 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:enterpriseOpsGym
τ²-Bench Telecom (AA)

Version snapshot-2026-09-10

Published board

Tests dual-control telecom agents that coordinate tool use with a simulated user.

0.99123 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ²-Bench Telecom (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.991228070175439 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:tau2
τ³-Banking (AA)

Version 1.0.1

Published board

Tests banking support agents that retrieve policies and change account state through tools.

0.34639 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ³-Banking (AA) · 1.0.1 · Published board
Exact value: 0.34639175257732 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:f7a4ea75-e548-4069-80d4-9be8bc7c009b:tauBanking
Missing coverage · 53 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

VariantCoding · snapshot 2026-09-10Intelligence · snapshot 2026-09-10
GLM-5.2 (max)68.838.6
GLM-5.2 (Non-reasoning)46.522.4

Token offers by platform — Adjusted $/task

Adjusted costs are modeled USD per task: AA output tokens × OpenRouter usage I/O (Chutes global fallback). These are general usage and benchmark proxies for coding-agent work. Missing AA data assumes 1,000 output tokens/task; unknown cache hit assumes 0%; unmeasured additional cache writes assume 0 tokens. Click any underlined price for exact inputs, dates and assumptions. Raw list prices use the selected fixed input/output blend, in USD per million tokens.

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

OpenRouter (24)

DeepInfraglobaldeepinfra/fp4$0.487 raw in $/1M$1.56 raw out $/1M
Ambientglobalambient/fp8$0.600 raw in $/1M$2.00 raw out $/1M
Novitaglobalnovita/fp8$0.683 raw in $/1M$2.15 raw out $/1M
DigitalOceanglobaldigitalocean$0.700 raw in $/1M$2.20 raw out $/1M
CoreWeaveglobalcoreweave/fp4$0.760 raw in $/1M$2.42 raw out $/1M
AtlasCloudglobalatlas-cloud/fp8$0.938 raw in $/1M$2.95 raw out $/1M
Inceptronglobalinceptron/fp4EU$1.25 raw in $/1M$2.99 raw out $/1M
Phalaglobalphala/fp8TEE$1.26 raw in $/1M$3.00 raw out $/1M
Mistralglobalmistral/zdrEU$1.40 raw in $/1M$4.40 raw out $/1M
MistralglobalmistralEU$1.40 raw in $/1M$4.40 raw out $/1M
BaseTenglobalbaseten/fp8$1.40 raw in $/1M$4.40 raw out $/1M
Crusoeglobalcrusoe/fp8$1.40 raw in $/1M$4.40 raw out $/1M
Togetherglobaltogether$1.40 raw in $/1M$4.40 raw out $/1M
Fireworksglobalfireworks$1.40 raw in $/1M$4.40 raw out $/1M
Veniceglobalvenice/fp8$1.40 raw in $/1M$4.40 raw out $/1M
GMICloudglobalgmicloud/fp8$1.40 raw in $/1M$4.40 raw out $/1M
Parasailglobalparasail/fp4$1.40 raw in $/1M$4.40 raw out $/1M
Friendliglobalfriendli$1.40 raw in $/1M$4.40 raw out $/1M
Cloudflareglobalcloudflare$1.40 raw in $/1M$4.40 raw out $/1M
Mistraleumistral/euEU$1.54 raw in $/1M$4.84 raw out $/1M
BaseTenglobalbaseten/fast$2.10 raw in $/1M$6.60 raw out $/1M
Fireworksglobalfireworks/fast-us$2.10 raw in $/1M$6.60 raw out $/1M
Fireworksglobalfireworks/fast$2.10 raw in $/1M$6.60 raw out $/1M
Decartglobaldecart/fast$2.10 raw in $/1M$6.60 raw out $/1M

Inceptron (1)

InceptroneuEU$1.25 raw in $/1M$2.99 raw out $/1M

Chutes (1)

ChutesglobalTEE$1.25 raw in $/1M$3.95 raw out $/1M

Nebius (1)

Nebiusuk$1.40 raw in $/1M$4.40 raw out $/1M

Mistral (1)

MistraleuEU$1.40 raw in $/1M$4.40 raw out $/1M

TensorX (1)

TensorXeuEU$1.50 raw in $/1M$4.50 raw out $/1M

Azure AI Foundry (1)

Azure AI Foundryusfireworks$1.54 raw in $/1M$4.84 raw out $/1M

T-Systems LLM Hub (1)

T-Systems LLM HubeuEU$1.74 raw in $/1M$4.07 raw out $/1M

Scaleway (1)

ScalewayeuEU$2.09 raw in $/1M$6.39 raw out $/1M
Benchmark Heaven — Model benchmarks & costs