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

GLM-5.3-Flash

open weights★ featured
Z.ai · released 2026-08-26 · 28 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$0.075$0.250
2RelaceOpenRouter$0.090$0.300
3WaferOpenRouter$0.100$0.350
4MorphOpenRouter$0.100$0.350
5GMICloudOpenRouter$0.112$0.375

Benchmarks

Composite77.4
Mean-imputed base87.7
Dominance adjustment-10.3
Composite evidence2/5
AA Coding · unversioned snapshot 2026-09-1071.5
AA Coding Agent · v1.4 · 2026-09-09
AA Intelligence · unversioned snapshot 2026-09-1041.9
DesignArena Frontend · unversioned snapshot 2026-09-10
DesignArena Full-Stack · unversioned snapshot 2026-09-10
Output speed (t/s)81

MODEL EVIDENCE

Benchmark sheet

15 / 73 registered benchmark versions covered · 17 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 · 16 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
AA-Briefcase

Version snapshot-2026-09-10

Published board

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

1454.58 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Briefcase · snapshot-2026-09-10 · Published board
Exact value: 1454.58 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:briefcaseBreakdown.overall.elo
GDPval-AA v2

Version 2

Published board

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

1669.27 Elomeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDPval-AA v2 · 2 · Published board
Exact value: 1669.27 Elo
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:gdpval
Terminal-Bench v2.1 (AA)

Version 2.1

Published board

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

0.8427 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v2.1 (AA) · 2.1 · Published board
Exact value: 0.842696629213483 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:terminalbenchV21
Terminal-Bench v4.0 (AA)

Version 4.0

Published board

Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

0.32828 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Terminal-Bench v4.0 (AA) · 4.0 · Published board
Exact value: 0.328282828282828 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:terminalbenchV40

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.

0.5162 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: SciCode (AA subproblems) · 1.0.1 · Published board
Exact value: 0.516203703703704 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae: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.

71.5 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Coding Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 71.5 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_coding_index:glm-5.3-flash::default
Protocol: inspect · file data/raw/artificialanalysis.json

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.

0.39852 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: Humanity's Last Exam (AA text-only) · snapshot-2026-09-10 · Published board
Exact value: 0.398517145505097 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:hle
AA-Omniscience Index

Version snapshot-2026-09-10

Published board

Tests factual reliability while rewarding correct answers and penalizing hallucinations.

7.46667 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-Omniscience Index · snapshot-2026-09-10 · Published board
Exact value: 7.46666666666667 points
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae: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.

0.154 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GDP.pdf (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.154 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:gdpPdfAllPass
AA-LCR v1.1

Version 1.1

Published board

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

0.8 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA-LCR v1.1 · 1.1 · Published board
Exact value: 0.8 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:lcr
MLCR-AA

Version snapshot-2026-09-10

Published board

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

0.51111 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: MLCR-AA · snapshot-2026-09-10 · Published board
Exact value: 0.511111111111111 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae: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.

41.9 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AA Intelligence Index · snapshot-2026-09-10 (unversioned) · Published board
Exact value: 41.9 points
Observed: 2026-09-10 · publication date: not recorded
Observation id: legacy:aa_intelligence_index:glm-5.3-flash::default
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.

0.15429 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: CritPt (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.154285714285714 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:critpt
GPQA Diamond (AA)

Version snapshot-2026-09-10

Published board

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

0.91212 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: GPQA Diamond (AA) · snapshot-2026-09-10 · Published board
Exact value: 0.912121212121212 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae: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.

0.60369 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: AutomationBench-AA · 1.0.6 · Published board
Exact value: 0.6036862782167782 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:automationBenchPartialScore
EnterpriseOps-Gym-AA

Version snapshot-2026-09-10

Published board

Tests enterprise workflows through MCP tools against resettable application environments.

0.33214 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: EnterpriseOps-Gym-AA · snapshot-2026-09-10 · Published board
Exact value: 0.3321396598030439 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:enterpriseOpsGym
τ³-Banking (AA)

Version 1.0.1

Published board

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

0.47216 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
Evidence
Axis: τ³-Banking (AA) · 1.0.1 · Published board
Exact value: 0.472164948453608 fraction
Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
Observation id: aa:19496b81-9f41-4214-a77a-1df803b3c5ae:tauBanking
Missing coverage · 60 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 — 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.

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

OpenRouter (23)

DeepInfraglobaldeepinfra/fp4$0.075 raw in $/1M$0.250 raw out $/1M
Relaceglobalrelace/fp4$0.090 raw in $/1M$0.300 raw out $/1M
Waferglobalwafer$0.100 raw in $/1M$0.350 raw out $/1M
GMICloudglobalgmicloud/fp8$0.112 raw in $/1M$0.375 raw out $/1M
Novitaglobalnovita/fp8$0.132 raw in $/1M$0.440 raw out $/1M
Makoraglobalmakora$0.140 raw in $/1M$0.470 raw out $/1M
Modalglobalmodal/fp8$0.150 raw in $/1M$0.500 raw out $/1M
Crusoeglobalcrusoe/fp4$0.150 raw in $/1M$0.500 raw out $/1M
CoreWeaveglobalcoreweave/fp8$0.150 raw in $/1M$0.500 raw out $/1M
Sail Researchglobalsail-research/fp8$0.150 raw in $/1M$0.500 raw out $/1M
NextBitglobalnextbit/fp8EU$0.150 raw in $/1M$0.500 raw out $/1M
Fireworksglobalfireworks$0.150 raw in $/1M$0.500 raw out $/1M
Phalaglobalphala/fp8TEE$0.150 raw in $/1M$0.500 raw out $/1M
DigitalOceanglobaldigitalocean$0.150 raw in $/1M$0.500 raw out $/1M
Togetherglobaltogether$0.150 raw in $/1M$0.500 raw out $/1M
Rekaglobalreka/fp8$0.150 raw in $/1M$0.500 raw out $/1M
Parasailglobalparasail/fp8$0.150 raw in $/1M$0.500 raw out $/1M
BaseTenglobalbaseten/fp8$0.150 raw in $/1M$0.500 raw out $/1M
Veniceglobalvenice$0.150 raw in $/1M$0.500 raw out $/1M
Io Netglobalio-net/fp8$0.150 raw in $/1M$0.500 raw out $/1M
Cloudflareglobalcloudflare$0.150 raw in $/1M$0.500 raw out $/1M
Friendliglobalfriendli$0.150 raw in $/1M$0.500 raw out $/1M
Morphglobalmorph/fp8$0.100 raw in $/1M$0.350 raw out $/1M

Nebius (1)

Nebiusus$0.150 raw in $/1M$0.500 raw out $/1M

TensorX (1)

TensorXeuEU$0.200 raw in $/1M$0.500 raw out $/1M
Benchmark Heaven — Model benchmarks & costs