BenchLeader

Qwen3.8 Max vs Qwen4 Max

Full profiles: Qwen3.8 Max (Alibaba) and Qwen4 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 13 sources

As of 19 Nov 2026, there are not enough shared benchmarks for a verdict, and Qwen4 Max is 1.3× cheaper at $2.25 vs $3.00 per 1M tokens blended. Choose Qwen3.8 Max for coding (61 vs 55); choose Qwen4 Max for reasoning (59 vs 51) and knowledge (59 vs 58).

Qwen4 Max was released on 16 Nov 2026 and has no BenchLeader Index yet (it needs five independent results across two categories). So this page gives no quality verdict: it compares what is published so far for both, price, context window, speed and the benchmarks both have results on. First results are tracked on Qwen4 Max's page.

Key facts (as of 19 Nov 2026)

  • Qwen3.8 Max costs $3.00 per 1M tokens blended (list price, 19 Nov 2026).
  • Qwen4 Max costs $2.25 per 1M tokens blended (list price, 19 Nov 2026).
  • Of the 17 benchmarks both models have, Qwen4 Max leads 15 (BenchLeader, 19 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingQwen3.8 Max61 vs 55 category score; FrontierCode 2.0 (AA) 23.4% vs 26.4%Medium
ReasoningQwen4 Max59 vs 51 category score; HLE-Diamond (AA) 44.9% vs 24.0%High
KnowledgeQwen4 Max59 vs 58 category score; AA-Omniscience v1.1 27.7 vs 10.5Medium
Chat quality (human preference)–Only Qwen3.8 Max has an Arena rating (68 category score)Not comparable
Lowest costQwen4 Max$2.25 vs $3.00 per 1M blended; agentic coding session $0.108 vs $0.144–
Fastest first answerQwen3.8 Max93.1 s (Qwen3.8 Max) vs 139.2 s (Qwen4 Max) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Not enough shared benchmarks for a verdict.
  • Qwen3.8 Max is stronger in coding.
  • Qwen4 Max is stronger in knowledge, reasoning.
  • Qwen4 Max is 1.3× cheaper ($2.25 vs $3.00 per 1M blended).

At a glance

SpecQwen3.8 MaxQwen4 Max
DeveloperAlibabaAlibaba
Released3 Aug 202616 Nov 2026
Context window (tokens)1,000,000991,808
Compared atQwen3.8 MaxQwen4 Max
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $6.00 / $0.250$1.50 / $4.50 / $0.071

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryQwen3.8 MaxQwen4 MaxLeader
Reasoning50.958.5Qwen4 Max
Coding61.055.1Qwen3.8 Max
Agents & tools65.0–not comparable
Maths64.9–not comparable
Knowledge58.059.0Qwen4 Max
Human preference67.5–not comparable
Multimodal65.5–not comparable
Long context64.8–not comparable
Composite43.3–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingKnowledgeQwen3.8 Max, Reasoning: 50.9Qwen3.8 Max, Coding: 61.0Qwen3.8 Max, Knowledge: 58.0Qwen4 Max, Reasoning: 58.5Qwen4 Max, Coding: 55.1Qwen4 Max, Knowledge: 59.0

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 17 benchmarks both have, Qwen3.8 Max leads 2, Qwen4 Max leads 15. Every overall index that rates both puts Qwen4 Max ahead.

Overall indexQwen3.8 MaxQwen4 MaxLeader
AA Intelligence Index v5.0.133.642.9Qwen4 Max

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureQwen3.8 MaxQwen4 Max
Blended price per 1M tokens$3.00$2.25
Input / output per 1M$2.00 / $6.00$1.50 / $4.50
Cached input per 1M$0.250$0.071
Price per task: chat reply$0.0026$0.0020
Price per task: summarize a 30-page report$0.028$0.021
Price per task: code edit$0.021$0.016
Price per task: agentic coding session$0.144$0.108
Price per task: structured extraction$0.0052$0.0039
Agentic coding session, input mostly cached$0.065$0.044
Cost per benchmark task (AA Index)$10.02$3.27
Output tokens per task (AA Index)171k105k
Of which reasoning120k69k
Time per task (AA Index)48 min30 min
Output speed60 tok/s59 tok/s
Time to first answer93.1 s139.2 s
Time to a complete answer, last measured 13 Nov 2026282.4 s–

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $10.02 on Qwen3.8 Max and $3.27 on Qwen4 Max, and Qwen3.8 Max wrote 1.6× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Qwen3.8 Max scores 59.0 and takes 93 s to its first answer token; Qwen3.8 Max (xhigh) scores 56.4 in 116 s. Qwen4 Max and takes 139 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

143 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherQwen3.8 MaxQwen4 Max
BenchLeader IndexBenchLeader59.0–
Agents & tools scoreBenchLeader65.0–
Coding scoreBenchLeader61.055.1
Composite scoreBenchLeader43.3–
Human preference scoreBenchLeader67.5–
Knowledge scoreBenchLeader58.059.0
Long context scoreBenchLeader64.8–
Maths scoreBenchLeader64.9–
Multimodal scoreBenchLeader65.5–
Reasoning scoreBenchLeader50.958.5
Blended price $/MBenchLeader$3.00$2.25
Output speedBenchLeader60 tok/s59 tok/s
Time to first answerBenchLeader93.1 s139.2 s
Context windowBenchLeader1,000,000 tokens991,808 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.7%†–
Arena Hard PromptsArena (LMArena)1507–
LiveBench 2.0 ReasoningLiveBench88.2%92.2%†
LiveBench 1.0 ReasoningLiveBench88.2%–
GPQA Diamond (AA)Artificial Analysis92.8%–
Humanity's Last Exam (AA)Artificial Analysis43.1%–
HLE-Diamond (AA)Artificial Analysis24.0%44.9%
GPQA Diamond (Vals)Vals AI93.7%–
CritPtArtificial Analysis20.0%–
CritPt v2 hard subset (AA)Artificial Analysis29.5%43.0%
MysteryMechanismVals AI23.9%–
Arena ExpertArena (LMArena)1514–
Chess PuzzlesEpoch AI Benchmarking Hub46.0%†–
Mystery Game PuzzlesEpoch AI Benchmarking Hub38.0%†–
LMCAEpoch AI Benchmarking Hub46.2%†–
DTBenchEpoch AI Benchmarking Hub92.0%†–
Coding
SciCodeSciCode53.2%–
Arena CodingArena (LMArena)1525–
Arena WebDevArena (LMArena)16751750†
LiveBench 2.0 CodingLiveBench60.9%69.8%†
LiveBench 1.0 CodingLiveBench72.9%–
LiveCodeBenchVals AI87.8%–
IOIVals AI68.9%–
SWE-bench (Vals)Vals AI85.6%–
Code MigrationVals AI24.0%–
Show all 143 benchmarks
MetricPublisherQwen3.8 MaxQwen4 Max
Coding
ProgramBenchVals AI0.0%–
SWE-bench MultimodalVals AI42.5%–
Vibe Code Bench 1-100Vals AI12.8%–
Vibe Code Bench v1.1Vals AI64.7%86.7%†
SWE Atlas v1.1Scale AI SEAL64.4%–
SWE Atlas v1.1: Codebase QnAScale AI SEAL81.5%–
SWE Atlas v1.1: Test WritingScale AI SEAL58.9%–
SWE Atlas v1.1: RefactoringScale AI SEAL52.9%–
MirrorCodeEpoch AI Benchmarking Hub52.2%†–
DeepSWE v1.1Epoch AI Benchmarking Hub57.5%†–
ALE-BenchEpoch AI Benchmarking Hub1679.1†–
FrontierSWEEpoch AI Benchmarking Hub17.8%†–
Terminal-Bench 4.0 (AA)Artificial Analysis38.9%48.5%
Terminal-Bench 2.1 (AA)Artificial Analysis88.8%–
Startrise FrontendStartrise71.3%–
GameBench 2 OverallDuelLab GameBench 254.2–
GameBench 2 by reasoning settingDuelLab GameBench 269.6†–
Design Arena WebsiteDesign Arena1272–
FrontierCode 1.1 (AA)Artificial Analysis43.2%–
FrontierCode 2.0 (AA)Artificial Analysis23.4%26.4%
Agents & tools
Terminal-BenchTerminal-Bench27.0%†–
APEX-AgentsMercor63.3%–
Arena AgentArena (LMArena)-0.97.3†
LiveBench Long AgenticLiveBench26.6%46.6%†
LiveBench BrowserLiveBench49.4%80.7%†
LiveBench Agentic CodingLiveBench64.7%–
Terminal-Bench 2.1 (Vals)Vals AI67.4%–
τ³-bench Bankingτ²-bench55.1%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis58.3%–
GDPval-AA v2.1Artificial Analysis16741809
τ³-Banking (AA)Artificial Analysis51.3%–
ITBench SRE (AA)Artificial Analysis40.3%–
Analyst Agent (AA)Artificial Analysis45.0%46.3%
APEX-Agents (AA)Artificial Analysis42.4%59.1%
CyberBenchVals AI28.6%–
Finance Agent v2Vals AI50.6%–
Finance Agent v2.1Vals AI–66.7%†
Harvey's Legal Agent Benchmark v1.1Vals AI–21.3%†
Harvey's Legal Agent Benchmark v1Vals AI10.4%–
Legal Research BenchVals AI47.6%41.4%†
Robo-benchVals AI5.2%†–
SkillsBenchVals AI42.0%–
Tax Agent BenchVals AI32.1%40.4%†
Terminal-Bench 4.0 (Vals)Vals AI34.3%48.5%†
Terminal-Bench ScienceVals AI12.9%–
Arena SearchArena (LMArena)1227–
Arena Agent Task CompletionArena (LMArena)3.68.8†
AutomationBenchArtificial Analysis56.2%72.6%
GDP.pdf (AA)Artificial Analysis22.8%26.2%
Harvey LAB-AA v1.1Harvey–9.4%
EnterpriseOps-GymArtificial Analysis47.6%48.5%
AA-Briefcase v1.1Artificial Analysis16041686
GDPxGDPx by SemiAnalysis3.5%†–
Design Arena AgenticDesign Arena12551356
Terminal-Bench-Science 0.1 (AA)Artificial Analysis11.9%23.3%
MKA (AA)Artificial Analysis37.4%–
FACTS SearchGoogle85.0%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub74.7%†–
FrontierMath Tier 4Epoch AI Benchmarking Hub46.3%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%†–
ProofBenchVals AI58.0%–
LiveBench MathematicsLiveBench91.3%–
Arena MathsArena (LMArena)1501–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub47.3%†–
LiveBench 2.0 Data AnalysisLiveBench78.4%83.4%†
LiveBench ResearchLiveBench72.8%84.7%†
LiveBench 1.0 Data AnalysisLiveBench78.4%–
AA-Omniscience v1.1Artificial Analysis10.527.7
MMLU-ProVals AI88.6%–
LegalBenchVals AI83.6%–
CorpFinVals AI65.8%–
TaxEvalVals AI75.5%–
Excel Modeling BenchmarkVals AI60.1%–
Excel Modeling Benchmark v1.1Vals AI66.0%70.8%†
MedCodeVals AI40.7%–
MedScribeVals AI85.0%–
Public Benefits Bench v1.1Vals AI67.1%–
Access to Justice BenchmarkVals AI76.4%–
Financial Coaching BenchVals AI75.6%–
Immigration BenchVals AI70.1%–
GDP.pdfEpoch AI Benchmarking Hub42.8%†–
AA-Omniscience v1.1: accuracyArtificial Analysis29.5%43.7%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis72.9%71.6%
FACTS ParametricGoogle30.8%–
Instruction following
LiveBench LanguageLiveBench79.7%–
LiveBench Instruction FollowingLiveBench74.1%–
Arena Instruction FollowingArena (LMArena)1478–
Human preference
Arena TextArena (LMArena)1484–
Arena Creative WritingArena (LMArena)1473–
Arena Multi-turnArena (LMArena)1495–
Arena Longer QueriesArena (LMArena)1498–
Multimodal
Arena VisionArena (LMArena)1312–
LiveBench DesignLiveBench76.6%79.1%†
MMMU-ProArtificial Analysis82.8%–
MMMU-Pro (Vals)Vals AI88.0%–
MortgageTaxVals AI64.0%–
SAGEVals AI81.8%–
Humanity's Sixth SenseScale AI SEAL33.0%†–
Furniture AssemblyEpoch AI Benchmarking Hub20.0%†–
VIALS-AAHandshake AI31.7%–
Code2Video-AAArtificial Analysis1021–
AA-3DArtificial Analysis954–
FACTS MultimodalGoogle51.5%–
Long context
AA-LCR v1.1Artificial Analysis80.3%–
MLCRArtificial Analysis26.1%19.4%
FACTS GroundingGoogle73.8%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.6–
LiveBench 2.0LiveBench60.9%73.1%†
LiveBench 1.0LiveBench78.5%–
AA Intelligence Index v5.0.1Artificial Analysis33.642.9
AA Intelligence Index v4.3.2Artificial Analysis45.4–
AA Progress Index v1Artificial Analysis323.7–
Vals IndexVals AI–63.2†
Vals Finance IndexVals AI–62.0%†
Vals RSI IndexVals AI21.8%†–
Vals Multimodal IndexVals AI65.4%–
Vals Legal IndexVals AI–70.7%†
Safety & honesty
DistressBenchScale AI SEAL77.6%–

Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Qwen3.8 Max: BenchLeader Index 63.8 → 59.1.
  • Qwen3.8 Max: 113 new results (FACTS Search, FACTS Grounding, FACTS Parametric…); 2 score revisions.
  • Qwen3.8 Max: 1 score revision.
  • Qwen3.8 Max: 1 score revision.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Qwen3.8 Max vs Qwen4 Max: questions

Qwen3.8 Max vs Qwen4 Max: which is cheaper, and will that change?
Qwen4 Max is cheaper today: $2.25 against $3.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Qwen3.8 Max or Qwen4 Max better for coding?
Qwen3.8 Max scores higher in coding (61 vs 55 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 23.4% for Qwen3.8 Max against 26.4% for Qwen4 Max.
Which is faster, Qwen3.8 Max or Qwen4 Max?
Qwen3.8 Max streams faster (60 vs 59 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Both take about 1M tokens: Qwen3.8 Max 1,000,000, Qwen4 Max 991,808.
Which has lower latency?
Qwen3.8 Max answers first: 93.1 s against 139.2 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
More questions (2)
Do independent benchmarks agree on Qwen3.8 Max vs Qwen4 Max?
Across the 17 benchmarks both have, Qwen3.8 Max leads 2, Qwen4 Max leads 15. Every overall index that rates both puts Qwen4 Max ahead.
When was Qwen4 Max released?
Qwen4 Max was released on 16 Nov 2026.