BenchLeader

Qwen3.7 Plus vs Qwen3.8 Max

Full profiles: Qwen3.7 Plus (Alibaba) and Qwen3.8 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 13 sources

As of 16 Nov 2026, Qwen3.7 Plus and Qwen3.8 Max are neck and neck on quality (57.6 vs 58.7 on the BenchLeader Index, inside the ±7.8 margin), and Qwen3.7 Plus is 4.3× cheaper at $0.700 vs $3.00 per 1M tokens blended. Choose Qwen3.7 Plus for reasoning (54 vs 52) and fast first answers (49.8 s vs 119.6 s); choose Qwen3.8 Max for coding (62 vs 44), agents & tools (59 vs 46), and long context (65 vs 61).

Key facts (as of 16 Nov 2026)

  • Qwen3.7 Plus scores 57.6 on the BenchLeader Index and Qwen3.8 Max scores 58.7 (BenchLeader, 16 Nov 2026).
  • Qwen3.7 Plus costs $0.700 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.8 Max costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 44 benchmarks both models have, Qwen3.8 Max leads 41 (BenchLeader, 16 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 Max62 vs 44 category score; SciCode 53.2% vs 46.1%High
Agents & tool useQwen3.8 Max59 vs 46 category score; τ³-Banking (AA) 51.3% vs 17.5%High
MathsQwen3.8 Max65 vs 64 category score; Arena Maths 1505 vs 1465Medium
ReasoningQwen3.7 Plus54 vs 52 category score; HLE-Diamond (AA) 13.9% vs 24.0%Medium
Long documentsQwen3.8 Max65 vs 61 category score; AA-LCR v1.1 80.3% vs 73.0%Medium
Images and other mediaQwen3.8 Max66 vs 62 category score; Arena Vision 1312 vs 1277Medium
Chat quality (human preference)Qwen3.8 Max68 vs 64 on Arena votesMedium
Lowest costQwen3.7 Plus$0.700 vs $3.00 per 1M blended; agentic coding session $0.030 vs $0.144–
Fastest first answerQwen3.7 Plus49.8 s (Qwen3.7 Plus) vs 119.6 s (Qwen3.8 Max (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

  • Qwen3.7 Plus and Qwen3.8 Max (max) are neck and neck on quality (57.6 vs 58.7, within the ±7.8 margin).
  • Qwen3.7 Plus is stronger in reasoning.
  • Qwen3.8 Max (max) is stronger in agents & tools, coding, human preference, long context, maths, multimodal.
  • Qwen3.7 Plus is 4.3× cheaper ($0.700 vs $3.00 per 1M blended).

At a glance

SpecQwen3.7 PlusQwen3.8 Max
DeveloperAlibabaAlibaba
Released2 Jun 20263 Aug 2026
Context window (tokens)1,000,0001,000,000
Compared atQwen3.7 PlusQwen3.8 Max (max)
Open weightsNoNo
Price in / out / cached input per 1M$0.400 / $1.60 / $0.080$2.00 / $6.00 / $0.250

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.

CategoryQwen3.7 PlusQwen3.8 Max (max)Leader
Reasoning54.451.5Qwen3.7 Plus
Coding43.961.6Qwen3.8 Max
Agents & tools45.558.5Qwen3.8 Max
Maths64.265.2Qwen3.8 Max
Knowledge–58.0not comparable
Instruction following75.9–not comparable
Human preference64.067.5Qwen3.8 Max
Multimodal62.365.7Qwen3.8 Max
Long context61.064.8Qwen3.8 Max
Composite–45.0not 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 avg75ReasoningCodingAgents & toolsMathsLong contextMultimodalHumanpreferenceQwen3.7 Plus, Reasoning: 54.4Qwen3.7 Plus, Coding: 43.9Qwen3.7 Plus, Agents & tools: 45.5Qwen3.7 Plus, Maths: 64.2Qwen3.7 Plus, Long context: 61.0Qwen3.7 Plus, Multimodal: 62.3Qwen3.7 Plus, Human preference: 64.0Qwen3.8 Max, Reasoning: 51.5Qwen3.8 Max, Coding: 61.6Qwen3.8 Max, Agents & tools: 58.5Qwen3.8 Max, Maths: 65.2Qwen3.8 Max, Long context: 64.8Qwen3.8 Max, Multimodal: 65.7Qwen3.8 Max, Human preference: 67.5

Not drawn, measured for fewer than two of these models: Knowledge, Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 44 benchmarks both have, Qwen3.7 Plus leads 3, Qwen3.8 Max leads 41. Every overall index that rates both puts Qwen3.8 Max ahead.

Overall indexQwen3.7 PlusQwen3.8 Max (max)Leader
BenchLeader Index57.658.7neck and neck
Arena Text14551484Qwen3.8 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.

MeasureQwen3.7 PlusQwen3.8 Max (max)
Blended price per 1M tokens$0.700$3.00
Input / output per 1M$0.400 / $1.60$2.00 / $6.00
Cached input per 1M$0.080$0.250
Price per task: chat reply$0.0006$0.0026
Price per task: summarize a 30-page report$0.0058$0.028
Price per task: code edit$0.0048$0.021
Price per task: agentic coding session$0.030$0.144
Price per task: structured extraction$0.0011$0.0052
Agentic coding session, input mostly cached$0.016$0.065
Cost per benchmark task (AA Index)–$10.02
Output tokens per task (AA Index)–171k
Of which reasoning–120k
Time per task (AA Index)–48 min
Output speed57 tok/s59 tok/s
Time to first answer49.8 s119.6 s
Time to a complete answer, last measured 13 Nov 2026114.8 s294.1 s

Each model is compared at its best-ranked reasoning-effort setting. Qwen3.7 Plus scores 57.6 and takes 50 s to its first answer token. Qwen3.8 Max (max) scores 58.7 and takes 120 s to its first answer token; Qwen3.8 Max (xhigh) scores 56.6 in 3 s. 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

142 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.

MetricPublisherQwen3.7 PlusQwen3.8 Max (max)
BenchLeader IndexBenchLeader57.658.7
Agents & tools scoreBenchLeader45.558.5
Coding scoreBenchLeader43.961.6
Human preference scoreBenchLeader64.067.5
Instruction following scoreBenchLeader75.9–
Long context scoreBenchLeader61.064.8
Maths scoreBenchLeader64.265.2
Multimodal scoreBenchLeader62.365.7
Reasoning scoreBenchLeader54.451.5
Composite scoreBenchLeader–45.0
Knowledge scoreBenchLeader–58.0
Blended price $/MBenchLeader$0.700$3.00
Output speedBenchLeader57 tok/s59 tok/s
Time to first answerBenchLeader49.8 s119.6 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub87.9%92.7%†
Arena Hard PromptsArena (LMArena)14731507
LiveBench 2.0 ReasoningLiveBench–88.2%
LiveBench 1.0 ReasoningLiveBench–88.2%
GPQA Diamond (AA)Artificial Analysis90.0%92.8%
Humanity's Last Exam (AA)Artificial Analysis35.6%43.1%
HLE-Diamond (AA)Artificial Analysis13.9%24.0%
GPQA Diamond (Vals)Vals AI–93.7%
CritPtArtificial Analysis9.1%20.0%
CritPt v2 hard subset (AA)Artificial Analysis–29.5%
MysteryMechanismVals AI–23.9%
Arena ExpertArena (LMArena)14851514
Chess PuzzlesEpoch AI Benchmarking Hub–46.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub17.0%38.0%†
LMCAEpoch AI Benchmarking Hub37.6%46.2%†
DTBenchEpoch AI Benchmarking Hub84.0%92.0%†
Coding
SciCodeSciCode46.1%53.2%
FrontierCodeCognition10.2%–
Arena CodingArena (LMArena)15001523
Arena WebDevArena (LMArena)–1676
LiveBench 2.0 CodingLiveBench–60.9%
LiveBench 1.0 CodingLiveBench–72.9%
LiveCodeBenchVals AI–87.8%
IOIVals AI–68.9%
SWE-bench (Vals)Vals AI–85.6%
Show all 142 benchmarks
MetricPublisherQwen3.7 PlusQwen3.8 Max (max)
Coding
Code MigrationVals AI12.9%24.0%
ProgramBenchVals AI–0.0%
SWE-bench MultimodalVals AI–42.5%
Vibe Code Bench 1-100Vals AI–12.8%
Vibe Code Bench v1.1Vals AI46.4%64.7%
SWE Atlas v1.1Scale AI SEAL–64.4%
SWE Atlas v1.1: Codebase QnAScale AI SEAL–81.5%
SWE Atlas v1.1: Test WritingScale AI SEAL–58.9%
SWE Atlas v1.1: RefactoringScale AI SEAL–52.9%
MirrorCodeEpoch AI Benchmarking Hub–52.2%†
DeepSWE v1.1Epoch AI Benchmarking Hub–57.5%†
ALE-BenchEpoch AI Benchmarking Hub–1679.1†
FrontierSWEEpoch AI Benchmarking Hub–17.8%†
Terminal-Bench 4.0 (AA)Artificial Analysis1.0%38.9%
Terminal-Bench 2.1 (AA)Artificial Analysis61.0%88.8%
Startrise FrontendStartrise–71.3%
GameBench 2 OverallDuelLab GameBench 2–54.2†
GameBench 2 by reasoning settingDuelLab GameBench 217.7†69.6†
Design Arena WebsiteDesign Arena12611269
FrontierCode 1.1 (AA)Artificial Analysis–43.2%
FrontierCode 2.0 (AA)Artificial Analysis–23.4%
Agents & tools
Terminal-BenchTerminal-Bench–27.0%
OSWorld-Verified 2.0OSWorld2.8%–
APEX-AgentsMercor–63.3%
Arena AgentArena (LMArena)-80.1
LiveBench Long AgenticLiveBench–26.6%
LiveBench BrowserLiveBench–49.4%
LiveBench Agentic CodingLiveBench–64.7%
Terminal-Bench HardArtificial Analysis47.0%–
τ²-Bench Telecom (AA)Artificial Analysis93.0%–
Terminal-Bench 2.1 (Vals)Vals AI52.8%67.4%
τ³-bench Bankingτ²-bench–55.1%†
GDPval-AA v2.1, normalised scoreArtificial Analysis13.3%58.3%
GDPval-AA v2.1Artificial Analysis7741674
τ³-Banking (AA)Artificial Analysis17.5%51.3%
ITBench SRE (AA)Artificial Analysis–40.3%
Analyst Agent (AA)Artificial Analysis–45.0%
APEX-Agents (AA)Artificial Analysis22.4%42.4%
CyberBenchVals AI–28.6%
Finance Agent v2Vals AI38.2%50.6%
Harvey's Legal Agent Benchmark v1Vals AI0.0%10.4%
Legal Research BenchVals AI16.4%47.6%
SkillsBenchVals AI54.3%42.0%
Tax Agent BenchVals AI10.5%32.1%
Terminal-Bench 4.0 (Vals)Vals AI–34.3%
Terminal-Bench ScienceVals AI–12.9%
Arena SearchArena (LMArena)–1227
Arena Agent Task CompletionArena (LMArena)-10.84.5
AutomationBenchArtificial Analysis17.4%56.2%
GDP.pdf (AA)Artificial Analysis12.2%22.8%
EnterpriseOps-GymArtificial Analysis40.6%47.6%
AA-Briefcase v1.1Artificial Analysis9151604
GDPxGDPx by SemiAnalysis–3.5%
Design Arena AgenticDesign Arena–1264
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–11.9%
MKA (AA)Artificial Analysis–37.4%
FACTS SearchGoogle–85.0%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub34.4%†74.7%†
FrontierMath Tier 4Epoch AI Benchmarking Hub–46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub93.3%100.0%†
ProofBenchVals AI–58.0%
LiveBench MathematicsLiveBench–91.3%
Arena MathsArena (LMArena)14651505
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–47.3%†
LiveBench 2.0 Data AnalysisLiveBench–78.4%
LiveBench ResearchLiveBench–72.8%
LiveBench 1.0 Data AnalysisLiveBench–78.4%
AA-Omniscience v1.1Artificial Analysis–10.5
MMLU-ProVals AI–88.6%
LegalBenchVals AI–83.6%
CorpFinVals AI–65.8%
TaxEvalVals AI–75.5%
Excel Modeling BenchmarkVals AI49.4%60.1%
Excel Modeling Benchmark v1.1Vals AI–66.0%
MedCodeVals AI–40.7%
MedScribeVals AI–85.0%
Public Benefits Bench v1.1Vals AI–67.1%
Access to Justice BenchmarkVals AI–76.4%
Financial Coaching BenchVals AI–75.6%
Immigration BenchVals AI–70.1%
GDP.pdfEpoch AI Benchmarking Hub–23.2%†
AA-Omniscience v1.1: accuracyArtificial Analysis–29.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–72.9%
FACTS ParametricGoogle–30.8%
Instruction following
LiveBench LanguageLiveBench–79.7%
LiveBench Instruction FollowingLiveBench–74.1%
IFBenchArtificial Analysis78.0%–
Arena Instruction FollowingArena (LMArena)14471478
Human preference
Arena TextArena (LMArena)14551484
Arena Creative WritingArena (LMArena)14311472
Arena Multi-turnArena (LMArena)14641495
Arena Longer QueriesArena (LMArena)14651496
Multimodal
Arena VisionArena (LMArena)12771312
LiveBench DesignLiveBench–76.6%
MMMU-ProArtificial Analysis80.5%82.8%
MMMU-Pro (Vals)Vals AI–88.0%
MortgageTaxVals AI66.2%64.0%
SAGEVals AI89.2%81.8%
Humanity's Sixth SenseScale AI SEAL–33.0%
Furniture AssemblyEpoch AI Benchmarking Hub–20.0%†
VIALS-AAHandshake AI–31.7%
Code2Video-AAArtificial Analysis–1021
AA-3DArtificial Analysis–954
FACTS MultimodalGoogle–51.5%
Long context
AA-LCR v1.1Artificial Analysis73.0%80.3%
Arena DocumentArena (LMArena)1446–
MLCRArtificial Analysis8.9%26.1%
FACTS GroundingGoogle–73.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub147.9157.6
LiveBench 2.0LiveBench–60.9%
LiveBench 1.0LiveBench–78.5%
AA Intelligence Index v5.0.1Artificial Analysis–33.6
AA Intelligence Index v4.3.2Artificial Analysis25.245.4
AA Progress Index v1Artificial Analysis283.9323.7
Vals RSI IndexVals AI–21.8%
Vals Multimodal IndexVals AI53.9%65.4%
Safety & honesty
DistressBenchScale AI SEAL–77.6%

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), 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 (max): 1 score revision.
  • Qwen3.8 Max (max): 1 score revision.
  • Qwen3.8 Max (max): 6 score revisions.
  • Qwen3.7 Plus: 1 score revision.
  • Qwen3.8 Max (max): 1 score revision.
  • Qwen3.7 Plus: 1 score revision.
  • Qwen3.8 Max (max): 1 new result (FACTS Search); 1 score revision.
  • Qwen3.7 Plus: Qwen3.7 Plus cached input price moved from $0.055/M to $0.080/M (45% up).
  • Qwen3.8 Max (max): 1 score revision; cached input price moved from $0.22/M to $0.25/M (13% up).
  • Qwen3.7 Plus: Qwen3.7 Plus cached input price moved from $0.080/M to $0.055/M (31% down).

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

Qwen3.7 Plus vs Qwen3.8 Max: questions

Is Qwen3.7 Plus better than Qwen3.8 Max?
Qwen3.7 Plus and Qwen3.8 Max (max) are neck and neck on quality (57.6 vs 58.7, within the ±7.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Qwen3.7 Plus vs Qwen3.8 Max: which is cheaper, and will that change?
Qwen3.7 Plus is cheaper today: $0.700 against $3.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Qwen3.7 Plus or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher in coding (62 vs 44 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 46.1% for Qwen3.7 Plus against 53.2% for Qwen3.8 Max.
Which is faster, Qwen3.7 Plus or Qwen3.8 Max?
Qwen3.8 Max streams faster (59 vs 57 output tokens per second, Artificial Analysis 7-day median).
Is Qwen3.7 Plus or Qwen3.8 Max better for agents and tool use?
Qwen3.8 Max scores higher in agentic tasks (59 vs 46 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 17.5% for Qwen3.7 Plus against 51.3% for Qwen3.8 Max.
More questions (4)
Which is better for long documents?
Qwen3.8 Max scores higher on long-context benchmarks (65 vs 61). Both accept 1,000,000 tokens of context.
Which has lower latency?
Qwen3.7 Plus answers first: 49.8 s against 119.6 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.
Do independent benchmarks agree on Qwen3.7 Plus vs Qwen3.8 Max?
Across the 44 benchmarks both have, Qwen3.7 Plus leads 3, Qwen3.8 Max leads 41. Every overall index that rates both puts Qwen3.8 Max ahead.
When was Qwen3.8 Max released?
Qwen3.8 Max was released on 3 Aug 2026.