Qwen3.8-Flash-Next
Output 49 tokens/sFirst token 1.4 sContext 256K tokens
Providers
A price exists, but your data filter hides it.
Alibaba is not on OpenRouter's list of providers that neither train on nor retain prompts, and such providers are left out while “Trains or keeps your data” is off.
Composite
2 of 7 inputs6 radar axes: DesignArena's two boards share one62.7
Thin data · 2/7Based on only 2 of 7 Composite inputs — treat this rank as uncertaindominance-adjusted from 70.4: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding v4.x 73.1Coding Agent v1.4 —AA Intelligence (est.) 30.0AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
18 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
1 of 19 values are Alibaba's own claims (†), not independent measurements; a matching independent result replaces a claim as soon as one exists.
Agentic
AA-Briefcase971,587 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 v2961,647 Elo
GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v2.1 (AA)9186.1%
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)8525.3%
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.
Coding
SciCode (AA subproblems) v1.0.15950.6%
SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.
SWE-bench Multilingualdeveloper's claim81.0%† self-reported by the developer
SWE-bench Multilingual published 2026-09-10 → · mini-SWE-agent harness — A 300-instance SWE-bench variant with tasks from 42 repositories across 9 programming languages.
AA Coding Index v4.x · frozen 2026-10-278673.1
AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task82$0.004
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 → · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
Knowledge
Humanity's Last Exam (AA text-only)8838.0%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index71-9.72
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
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 v1.18679.7%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Reasoning
LiveBench 2026-06-254676.2
LiveBench 2026-06-25 → · Published board — A periodically refreshed suite of objectively graded tasks with separate category scores and an overall category mean.
Science
CritPt (AA)8511.1%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)9492.3%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)6083.3%
GPQA Diamond (OpenRouter run) published 2026-09-15 → · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
AutomationBench-AA v1.0.68055.9%
AutomationBench-AA v1.0.6 → · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
τ³-Banking (AA) v1.0.19445.4%
τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Vision
MMMU Pro (AA)8379.8%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
Missing coverage · 301 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 · 0 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
0 offers within the active global filters, 2 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
All 2 offers of this model are outside the active global filters.