← All models

Qwen3.8 2.4T A95B

open weights★ featured
Alibaba · released 2026-08-12 · 8 offers

Output 39 tokens/sFirst token 1.8 sContext 984K 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
3SiliconFlow
4Venice
5Modal

Composite

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

80.8

includes −1.3 for its Benchmaxxing signal (from 82.1; why, switch off in Options)

dominance-adjusted from 88.0: a better-measured model that is at least as good on each of these inputs ranks above it

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 85AA Intelligence: percentile 95AA Agentic: percentile 90

AA Coding 71.9Coding Agent v1.4 AA Intelligence 40.0AA Agentic 50.4Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

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

Compare this model →

Agentic

  • AA-Briefcase841,439 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 v2931,628 Elo

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

  • Terminal-Bench v2.1 (AA)8482.0%

    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)7011.1%

    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.

  • τ²-Bench Airline (OpenRouter run)8776.7%

    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 Index9050.4

    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

  • SciCode (AA subproblems) v1.0.17554.1%

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

  • AA Coding Index8571.9

    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.

Efficiency

Knowledge

Long-context

  • GDP.pdf (AA)6415.6%

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

  • AA-LCR v1.19180.3%

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

  • MLCR-AA10.0%

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

Reasoning

Science

Tool-use

  • AutomationBench-AA v1.0.68657.2%

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

  • EnterpriseOps-Gym-AA8747.4%

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

  • τ³-Banking (AA) v1.0.19849.1%

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

Missing coverage · 123 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 · 7 offers (Adjusted $/task)

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

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

OpenRouter (6)

DeepInfra
Novita
SiliconFlow
Venice
Modal
Together

TensorX (1)

TensorX
Qwen3.8 2.4T A95B — benchmarks & cost | Benchmark Heaven