BenchLeader

Gemini 3.6 Flash vs Qwen3.8 Max

Full profiles: Gemini 3.6 Flash (Google) and Qwen3.8 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 15 sources

As of 16 Nov 2026, Gemini 3.6 Flash and Qwen3.8 Max are neck and neck on quality (61.0 vs 58.7 on the BenchLeader Index, inside the ±4.5 margin), and Gemini 3.6 Flash is 2.0× cheaper at $1.50 vs $3.00 per 1M tokens blended. Choose Gemini 3.6 Flash for reasoning (64 vs 52) and knowledge (64 vs 58) and fast first answers (11.0 s vs 119.6 s), where it also streams 3×+ faster; choose Qwen3.8 Max for maths (65 vs 59) and coding (62 vs 57). Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 16 Nov 2026)

  • Gemini 3.6 Flash scores 61.0 on the BenchLeader Index and Qwen3.8 Max scores 58.7 (BenchLeader, 16 Nov 2026).
  • Gemini 3.6 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
  • Qwen3.8 Max costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Gemini 3.6 Flash streams 3×+ faster than Qwen3.8 Max (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 60 benchmarks both models have, Qwen3.8 Max leads 42 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Gemini 3.6 Flash is rated 1538 and Qwen3.8 Max 1676 (LMArena, as published by 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 57 category score; Arena WebDev 1676 vs 1538Medium
Agents & tool useEither59 vs 59 category score; τ³-Banking (AA) 29.9% vs 51.3%Either
MathsQwen3.8 Max65 vs 59 category score; Arena Maths 1505 vs 1501Medium
ReasoningGemini 3.6 Flash64 vs 52 category score; Arena Hard Prompts 1501 vs 1507High
KnowledgeGemini 3.6 Flash64 vs 58 category score; MMLU-Pro 89.3% vs 88.6%Medium
Long documentsEither65 vs 65 category score; AA-LCR v1.1 80.0% vs 80.3%Either
Images and other mediaEither65 vs 66 category score; Arena Vision 1297 vs 1312Either
Chat quality (human preference)Either67 vs 68 on Arena votesEither
Lowest costGemini 3.6 Flash (until 31 Dec 2026)$1.50 vs $3.00 per 1M blended; agentic coding session $0.060 vs $0.144; from 1 Jan 2027: $3.00 vs $3.00–
Fastest first answerGemini 3.6 Flash11.0 s (Gemini 3.6 Flash (high)) 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

  • Gemini 3.6 Flash (high) and Qwen3.8 Max (max) are neck and neck on quality (61.0 vs 58.7, within the ±4.5 margin).
  • Gemini 3.6 Flash (high) is stronger in agents & tools, knowledge, reasoning.
  • Qwen3.8 Max (max) is stronger in coding, human preference, long context, maths, multimodal.
  • Gemini 3.6 Flash (high) is 2.0× cheaper ($1.50 vs $3.00 per 1M blended) until 31 Dec 2026, then $3.00 vs $3.00 from 1 Jan 2027.
  • Gemini 3.6 Flash (high) streams 3.0× faster (177 vs 59 tokens per second).

At a glance

SpecGemini 3.6 FlashQwen3.8 Max
DeveloperGoogleAlibaba
Released21 Jul 20263 Aug 2026
Context window (tokens)1,048,5761,000,000
Compared atGemini 3.6 Flash (high)Qwen3.8 Max (max)
Open weightsNoNo
Price in / out / cached input per 1M$0.750 / $3.75 / $0.075$2.00 / $6.00 / $0.250
Announced price change$1.50 / $7.50 / $0.150 from 1 Jan 2027None announced

Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

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.

CategoryGemini 3.6 Flash (high)Qwen3.8 Max (max)Leader
Reasoning63.651.5Gemini 3.6 Flash
Coding56.761.6Qwen3.8 Max
Agents & tools59.258.5level
Maths59.065.2Qwen3.8 Max
Knowledge63.658.0Gemini 3.6 Flash
Human preference67.367.5level
Multimodal65.065.7level
Long context64.664.8level
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 & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceGemini 3.6 Flash, Reasoning: 63.6Gemini 3.6 Flash, Coding: 56.7Gemini 3.6 Flash, Agents & tools: 59.2Gemini 3.6 Flash, Maths: 59.0Gemini 3.6 Flash, Knowledge: 63.6Gemini 3.6 Flash, Long context: 64.6Gemini 3.6 Flash, Multimodal: 65.0Gemini 3.6 Flash, Human preference: 67.3Qwen3.8 Max, Reasoning: 51.5Qwen3.8 Max, Coding: 61.6Qwen3.8 Max, Agents & tools: 58.5Qwen3.8 Max, Maths: 65.2Qwen3.8 Max, Knowledge: 58.0Qwen3.8 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: Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 60 benchmarks both have, Gemini 3.6 Flash leads 16, Qwen3.8 Max leads 42 and 2 are tied. Every overall index that rates both puts Qwen3.8 Max ahead.

Overall indexGemini 3.6 Flash (high)Qwen3.8 Max (max)Leader
BenchLeader Index61.058.7neck and neck
Arena Text14831484Qwen3.8 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.

MeasureGemini 3.6 Flash (high)Qwen3.8 Max (max)
Blended price per 1M tokens, until 31 Dec 2026$1.50$3.00
Input / output per 1M$0.750 / $3.75$2.00 / $6.00
Blended price per 1M from 1 Jan 2027$3.00$3.00
Input / output per 1M from 1 Jan 2027$1.50 / $7.50$2.00 / $6.00
Cached input per 1M$0.075$0.250
Price per task: chat reply$0.0014$0.0026
Price per task: summarize a 30-page report$0.011$0.028
Price per task: code edit$0.010$0.021
Price per task: agentic coding session$0.060$0.144
Price per task: structured extraction$0.0023$0.0052
Agentic coding session, input mostly cached$0.030$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 speed177 tok/s59 tok/s
Time to first answer11.0 s119.6 s
Time to a complete answer, last measured 13 Nov 202630.3 s294.1 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.6 Flash (high) scores 61.0 and takes 11 s to its first answer token; Gemini 3.6 Flash scores 49.3 in 1 s. 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

148 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.

MetricPublisherGemini 3.6 Flash (high)Qwen3.8 Max (max)
BenchLeader IndexBenchLeader61.058.7
Agents & tools scoreBenchLeader59.258.5
Coding scoreBenchLeader56.761.6
Human preference scoreBenchLeader67.367.5
Knowledge scoreBenchLeader63.658.0
Long context scoreBenchLeader64.664.8
Maths scoreBenchLeader59.065.2
Multimodal scoreBenchLeader65.065.7
Reasoning scoreBenchLeader63.651.5
Composite scoreBenchLeader–45.0
Blended price $/MBenchLeader$1.50$3.00
Output speedBenchLeader177 tok/s59 tok/s
Time to first answerBenchLeader11.0 s119.6 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.1%92.7%†
Arena Hard PromptsArena (LMArena)15011507
LiveBench 2.0 ReasoningLiveBench–88.2%
LiveBench 1.0 ReasoningLiveBench85.2%88.2%
GPQA Diamond (AA)Artificial Analysis92.8%92.8%
Humanity's Last Exam (AA)Artificial Analysis40.8%43.1%
HLE-Diamond (AA)Artificial Analysis–24.0%
GPQA Diamond (Vals)Vals AI93.4%93.7%
ARC-AGI-1ARC Prize91.2%–
ARC-AGI-2ARC Prize60.4%–
CritPtArtificial Analysis10.6%20.0%
CritPt v2 hard subset (AA)Artificial Analysis–29.5%
MysteryMechanismVals AI–23.9%
Arena ExpertArena (LMArena)15001514
Chess PuzzlesEpoch AI Benchmarking Hub40.0%46.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub30.0%38.0%†
LMCAEpoch AI Benchmarking Hub44.9%46.2%†
DTBenchEpoch AI Benchmarking Hub95.5%92.0%†
ForecastBenchForecastBench65.7%†–
Coding
SciCodeSciCode53.4%53.2%
WeirdMLWeirdML56.1%–
FrontierCodeCognition34.4%†–
Arena CodingArena (LMArena)15181523
Arena WebDevArena (LMArena)15381676
LiveBench 2.0 CodingLiveBench–60.9%
Show all 148 benchmarks
MetricPublisherGemini 3.6 Flash (high)Qwen3.8 Max (max)
Coding
LiveBench 1.0 CodingLiveBench77.9%72.9%
LiveCodeBenchVals AI88.1%87.8%
IOIVals AI35.1%68.9%
SWE-bench (Vals)Vals AI79.6%85.6%
Code MigrationVals AI30.9%24.0%
ProgramBenchVals AI0.0%0.0%
SWE-bench MultimodalVals AI–42.5%
Vibe Code Bench 1-100Vals AI–12.8%
Vibe Code Bench v1.1Vals AI64.0%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 Hub23.3%52.2%†
DeepSWE v1.1Epoch AI Benchmarking Hub46.7%57.5%†
ALE-BenchEpoch AI Benchmarking Hub715.51679.1†
FrontierSWEEpoch AI Benchmarking Hub–17.8%†
Terminal-Bench 4.0 (AA)Artificial Analysis7.1%38.9%
Terminal-Bench 2.1 (AA)Artificial Analysis77.5%88.8%
Startrise FrontendStartrise–71.3%
GameBench 2 OverallDuelLab GameBench 250.6†54.2†
GameBench 2 by reasoning settingDuelLab GameBench 263.069.6†
Design Arena WebsiteDesign Arena1292†1269
FrontierCode 1.1 (AA)Artificial Analysis–43.2%
FrontierCode 2.0 (AA)Artificial Analysis–23.4%
Agents & tools
Terminal-BenchTerminal-Bench–27.0%
APEX-AgentsMercor46.9%†63.3%
Arena AgentArena (LMArena)–0.1
LiveBench Long AgenticLiveBench–26.6%
LiveBench BrowserLiveBench–49.4%
LiveBench Agentic CodingLiveBench43.4%64.7%
Terminal-Bench 2.1 (Vals)Vals AI73.8%67.4%
τ³-bench Bankingτ²-bench–55.1%†
GDPval-AA v2.1, normalised scoreArtificial Analysis–58.3%
GDPval-AA v2.1Artificial Analysis12931674
τ³-Banking (AA)Artificial Analysis29.9%51.3%
ITBench SRE (AA)Artificial Analysis–40.3%
Analyst Agent (AA)Artificial Analysis–45.0%
APEX-Agents (AA)Artificial Analysis–42.4%
CyberBenchVals AI45.4%28.6%
Finance Agent v2Vals AI56.3%50.6%
Harvey's Legal Agent Benchmark v1Vals AI3.3%10.4%
Legal Research BenchVals AI25.0%47.6%
SkillsBenchVals AI–42.0%
Tax Agent BenchVals AI18.0%32.1%
Terminal-Bench 4.0 (Vals)Vals AI–34.3%
Terminal-Bench ScienceVals AI4.3%12.9%
Arena SearchArena (LMArena)–1227
Arena Agent Task CompletionArena (LMArena)–4.5
AutomationBenchArtificial Analysis53.0%56.2%
GDP.pdf (AA)Artificial Analysis17.4%22.8%
EnterpriseOps-GymArtificial Analysis–47.6%
AA-Briefcase v1.1Artificial Analysis9571604
GDPxGDPx by SemiAnalysis–3.5%
Design Arena AgenticDesign Arena1177†1264
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–11.9%
MKA (AA)Artificial Analysis–37.4%
FACTS SearchGoogle75.7%†85.0%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub59.0%74.7%†
FrontierMath Tier 4Epoch AI Benchmarking Hub21.9%46.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub94.2%100.0%†
ProofBenchVals AI36.0%†58.0%
LiveBench MathematicsLiveBench86.4%91.3%
AIME 2026MathArena96.7%†–
HMMT February 2026MathArena89.4%†–
MathArena ApexMathArena26.0%†–
Arena MathsArena (LMArena)15011505
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub66.2%47.3%†
LiveBench 2.0 Data AnalysisLiveBench–78.4%
LiveBench ResearchLiveBench–72.8%
LiveBench 1.0 Data AnalysisLiveBench63.0%78.4%
AA-Omniscience v1.1Artificial Analysis–10.5
MMLU-ProVals AI89.3%88.6%
LegalBenchVals AI86.7%83.6%
CorpFinVals AI63.3%65.8%
TaxEvalVals AI74.9%75.5%
BioMysteryBenchVals AI58.5%–
Excel Modeling BenchmarkVals AI65.4%60.1%
Excel Modeling Benchmark v1.1Vals AI–66.0%
MedCodeVals AI53.1%40.7%
MedScribeVals AI79.7%85.0%
Public Benefits Bench v1.1Vals AI56.6%67.1%
Access to Justice BenchmarkVals AI–76.4%
Financial Coaching BenchVals AI65.8%75.6%
Immigration BenchVals AI–70.1%
GDP.pdfEpoch AI Benchmarking Hub14.0%23.2%†
AA-Omniscience v1.1: accuracyArtificial Analysis–29.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–72.9%
FACTS ParametricGoogle73.9%†30.8%
Instruction following
LiveBench LanguageLiveBench83.9%79.7%
LiveBench Instruction FollowingLiveBench75.4%74.1%
Arena Instruction FollowingArena (LMArena)14731478
Human preference
Arena TextArena (LMArena)14831484
EQ-Bench Creative Writing v3EQ-Bench1602†–
Arena Creative WritingArena (LMArena)14711472
Arena Multi-turnArena (LMArena)14901495
Arena Longer QueriesArena (LMArena)14851496
Multimodal
Arena VisionArena (LMArena)12971312
LiveBench DesignLiveBench–76.6%
MMMU-ProArtificial Analysis83.2%82.8%
MMMU-Pro (Vals)Vals AI88.4%88.0%
MortgageTaxVals AI67.6%64.0%
SAGEVals AI–81.8%
Humanity's Sixth SenseScale AI SEAL31.9%33.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub31.2%†–
Furniture AssemblyEpoch AI Benchmarking Hub23.3%20.0%†
VIALS-AAHandshake AI–31.7%
Code2Video-AAArtificial Analysis–1021
AA-3DArtificial Analysis–954
FACTS MultimodalGoogle53.7%†51.5%
Long context
AA-LCR v1.1Artificial Analysis80.0%80.3%
Arena DocumentArena (LMArena)1454–
MLCRArtificial Analysis10.0%26.1%
FACTS GroundingGoogle66.6%†73.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub155.2†157.6
LiveBench 2.0LiveBench–60.9%
LiveBench 1.0LiveBench73.6%78.5%
AA Intelligence Index v5.0.1Artificial Analysis–33.6
AA Intelligence Index v4.3.2Artificial Analysis34.045.4
AA Progress Index v1Artificial Analysis305.7323.7
Vals RSI IndexVals AI–21.8%
Vals Multimodal IndexVals AI65.1%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

  • Gemini 3.6 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
  • Qwen3.8 Max (max): 1 score revision.
  • Gemini 3.6 Flash (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1); 1 score revision.
  • Qwen3.8 Max (max): 1 score revision.
  • Gemini 3.6 Flash (high): 1 new result (MirrorCode); 1 score revision.
  • Qwen3.8 Max (max): 6 score revisions.
  • Qwen3.8 Max (max): 1 score revision.
  • Qwen3.8 Max (max): 1 new result (FACTS Search); 1 score revision.
  • Gemini 3.6 Flash (high): 1 score revision.
  • Qwen3.8 Max (max): 1 score revision; cached input price moved from $0.22/M to $0.25/M (13% up).

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

Gemini 3.6 Flash vs Qwen3.8 Max: questions

Is Gemini 3.6 Flash better than Qwen3.8 Max?
Gemini 3.6 Flash (high) and Qwen3.8 Max (max) are neck and neck on quality (61.0 vs 58.7, within the ±4.5 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.
Gemini 3.6 Flash vs Qwen3.8 Max: which is cheaper, and will that change?
Gemini 3.6 Flash is cheaper today: $1.50 against $3.00 per million tokens, blended at three input tokens per output token. Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Gemini 3.6 Flash or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher in coding (62 vs 57 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1538 for Gemini 3.6 Flash against 1676 for Qwen3.8 Max.
Which is faster, Gemini 3.6 Flash or Qwen3.8 Max?
Gemini 3.6 Flash streams 3×+ faster (177 vs 59 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.6 Flash or Qwen3.8 Max better for agents and tool use?
They are level in agentic tasks (59 vs 59 on the category index). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 29.9% for Gemini 3.6 Flash against 51.3% for Qwen3.8 Max.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (65 vs 65). Both take about 1M tokens: Gemini 3.6 Flash 1,048,576, Qwen3.8 Max 1,000,000.
Which has lower latency?
Gemini 3.6 Flash answers first: 11.0 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 Gemini 3.6 Flash vs Qwen3.8 Max?
Across the 60 benchmarks both have, Gemini 3.6 Flash leads 16, Qwen3.8 Max leads 42 and 2 are tied. 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.