← All models

Qwen3.8 27B (Non-reasoning)

open weights
Alibaba · released 2026-08-14 · 24 offers

Output 49 tokens/sFirst token 1.2 sContext 256K 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
2Phala
3Chutes
4Chutes
5Parasail

Composite

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

49.4

includes −1.6 for its Benchmaxxing signal (from 51.0; why, switch off in Options)

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 50AA Intelligence: percentile 75

AA Coding 44.6Coding Agent v1.4 AA Intelligence 22.4AA Agentic Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

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

Compare this model →

Agentic

  • GDPval-AA v2591,137 Elo

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

  • Terminal-Bench v2.1 (AA)4849.1%

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

Coding

  • SciCode (AA subproblems) v1.0.11736.2%

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

  • AA Coding Index5044.6

    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.

Knowledge

Long-context

  • AA-LCR v1.16569.3%

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

Reasoning

Safety/Alignment

Science

Tool-use

  • τ³-Banking (AA) v1.0.15220.0%

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

Vision

Unusual results

1 threshold-crossing signal flagged · 14 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.

Missing coverage · 131 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
Qwen3.8 27B (xhigh)68.133.9
Qwen3.8 27B (low)58.226.5
Qwen3.8 27B (medium)56.127.8
Qwen3.8 27B (Non-reasoning)44.622.4
Token offers by platform · 21 offers (Adjusted $/task)

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

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

OpenRouter (14)

ModelRunfreeFree route: rate- and quota-limited, availability may change — not used as a paid pricenot a paid price
DeepInfra
Phala
Chutes
Parasail
DekaLLM
AkashML
Ionstream
Reka
Mancer 2
Novita
Io Net
CoreWeave
Venice

Chutes (1)

Chutes

TensorX (1)

TensorX

TrustedTokens (1)

TrustedTokens

Scaleway (1)

Scaleway

STACKIT (1)

STACKIT

IONOS (1)

IONOS

OVHcloud (1)

OVHcloud
Qwen3.8 27B (Non-reasoning) — benchmarks & cost | Benchmark Heaven