AIEvals

Models

Qwen3.8-Flash-Next

Specifications and API prices for Qwen3.8-Flash-Next, recorded by Artificial Analysis.

AlibabaReleased 26 August 2026Context 256k tokensOutput Not published in the checked sourceOpen weights$0.15 in / $0.47 out per Mtok

Family Qwen3.8-Flash-Next15 benchmarks with a published resultNo first place on the independent columns among the 46 models this site listsRead 17 October 2026

Where it stands

Rank compares tracked models with a score. Published shows the source’s rank and field size, when available.

BenchmarkScoreRankPublishedLeaderBehind
Artificial Analysis Intelligence IndexArtificial Analysis4025of 42no list readClaude Opus 5.518 pts
Terminal-Bench 4.0Artificial Analysis25.25%21of 40no list readClaude Sonnet 5.538.39 pts
τ³-BankingArtificial Analysis45.36%9of 30no list readQwen3.8 Max5.98 pts
AutomationBench-AAArtificial Analysis55.91%26of 40no list readGemini 4 Argon21.60 pts
SciCodeArtificial Analysis50.58%37of 40no list readClaude Opus 5.516.32 pts
GDP.pdfArtificial Analysis15.60%29of 40no list readGPT-6.1 Sol15.40 pts
CritPtArtificial Analysis11.14%39of 42no list readGPT-5.6 Sol21.15 pts
AA-OmniscienceArtificial Analysis-9.7239of 42no list readClaude Opus 5.556.14
AA-LCR v1.1Artificial Analysis79.67%30of 42no list readKimi K39.00 pts
GDPval-AA v2.1Artificial Analysis1,612.1313of 42no list readClaude Opus 5.5234.04
AA-Briefcase v1.1Artificial Analysis1,587.577of 41no list readClaude Opus 5.5234.28
Humanity's Last ExamArtificial Analysis38.04%39of 42no list readClaude Opus 5.523.31 pts

Nearby on Artificial Analysis Intelligence Index

The two models above and below on the Artificial Analysis Intelligence Index (Artificial Analysis), on every column where this model has a published number.

ModelArtificial Analysis Intelligence IndexindexTerminal-Bench 4.0%
Muse Spark 1.2Meta407.07%
Qwen3.8 2.4T A95BAlibaba4011.11%
Qwen3.8-Flash-NextAlibaba4025.25%
Qwen3.8 MaxAlibaba4018.69%
DeepSeek V4.1 FlashDeepSeek3926.77%
Bold marks a figure better than this model’s on the same column, whichever model it belongs to. Ranks cover the models shown from the stated source.

Cost and speed, as published

Additional measurements from Artificial Analysis’ own row. Read 30 September 2026.

As publishedCost per taskOutput speed
Qwen3.8-Flash-Next$0.3758.4 tok/s

Results by benchmark

Independent and vendor results retain their own harnesses and effort settings.

BenchmarkIndependent runAs reported by a publisher
τ³-BankingTool use45.36%Artificial Analysisnot published
AutomationBench-AAWorkflow automation55.91%Artificial Analysisnot published
SciCodeScientific coding50.58%Artificial Analysisnot published
GDP.pdfDocument reasoning15.60%Artificial Analysisnot published
CritPtScientific reasoning11.14%Artificial Analysisnot published
AA-OmniscienceFactual knowledge-9.72Artificial Analysisnot published
AA-LCR v1.1Long-context reasoning79.67%Artificial Analysisnot published
Terminal-Bench 4.0Agentic coding25.25%Artificial Analysisnot published
Terminal-Bench 2.1Agentic coding
86.14%Artificial Analysis
not published
GPQA DiamondScience reasoning
92.32%Artificial Analysis
not published
MMMU ProMultimodal reasoning
79.77%Artificial Analysis
not published
GDPval-AA v2.1Knowledge work1,612.13Artificial Analysisnot published
AA-Briefcase v1.1Knowledge work1,587.57Artificial Analysisnot published
Humanity's Last ExamMultidisciplinary reasoning38.04%Artificial Analysisnot published
Artificial Analysis Intelligence IndexComposite40Artificial Analysisnot published
Independent column: the suite named under each figure, one harness per suite. Publisher column: each lab’s own table, reproduced on the benchmark’s page. Publisher ranks compare reported scores in the same table row only; ties share a rank and unreported cells are excluded.

Sources

Read on 17 October 2026.