BenchLeader

Gemini 3 Pro vs Qwen3.7 Max

Full profiles: Gemini 3 Pro (Google) and Qwen3.7 Max (Alibaba): every benchmark, price and rank.

Updated · Data from 12 sources

As of 19 Nov 2026, Gemini 3 Pro and Qwen3.7 Max are neck and neck on quality (60.0 vs 59.8 on the BenchLeader Index, inside the ±5.0 margin), and Qwen3.7 Max is 1.2× cheaper at $3.75 vs $4.50 per 1M tokens blended. Choose Gemini 3 Pro for agents & tools (59 vs 49), maths (63 vs 58), and coding (61 vs 59); choose Qwen3.7 Max for instruction following (78 vs 69) and long context (64 vs 63).

Key facts (as of 19 Nov 2026)

  • Gemini 3 Pro scores 60.0 on the BenchLeader Index and Qwen3.7 Max scores 59.8 (BenchLeader, 19 Nov 2026).
  • Gemini 3 Pro costs $4.50 per 1M tokens blended (list price, 19 Nov 2026).
  • Qwen3.7 Max costs $3.75 per 1M tokens blended (list price, 19 Nov 2026).
  • Of the 17 benchmarks both models have, Qwen3.7 Max leads 13 (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
CodingGemini 3 Pro61 vs 59 category score; SWE-bench (Vals) 76.4% vs 68.8%Medium
Agents & tool useGemini 3 Pro59 vs 49 category score; Terminal-Bench Hard 41.7% vs 50.8%High
MathsGemini 3 Pro63 vs 58 category scoreMedium
KnowledgeEither60 vs 61 category score; LegalBench 87.0% vs 84.9%Either
Long documentsQwen3.7 Max64 vs 63 category score; AA-LCR v1.1 79.0% vs 76.0%Medium
Following instructionsQwen3.7 Max78 vs 69 category score; IFBench 80.5% vs 70.4%High
Chat quality (human preference)–Only Qwen3.7 Max has an Arena rating (56 category score)Not comparable
Lowest costQwen3.7 Max$3.75 vs $4.50 per 1M blended; agentic coding session $0.180 vs $0.168–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 3 Pro (high) and Qwen3.7 Max are neck and neck on quality (60.0 vs 59.8, within the ±5.0 margin).
  • Gemini 3 Pro (high) is stronger in agents & tools, coding, maths.
  • Qwen3.7 Max is stronger in instruction following, knowledge, long context.
  • Qwen3.7 Max is 1.2× cheaper ($3.75 vs $4.50 per 1M blended).

At a glance

SpecGemini 3 ProQwen3.7 Max
DeveloperGoogleAlibaba
Released18 Nov 202519 May 2026
Context window (tokens)1,000,0001,000,000
Compared atGemini 3 Pro (high)Qwen3.7 Max
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $12.00 / –$2.50 / $7.50 / $0.500

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 Pro (high)Qwen3.7 MaxLeader
Reasoning–64.2not comparable
Coding61.058.6Gemini 3 Pro
Agents & tools59.448.6Gemini 3 Pro
Maths63.157.5Gemini 3 Pro
Knowledge60.060.9level
Instruction following69.378.1Qwen3.7 Max
Human preference–55.6not comparable
Multimodal62.2–not comparable
Long context62.664.1Qwen3.7 Max

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 avg75CodingAgents & toolsMathsKnowledgeInstructionfollowingLong contextGemini 3 Pro, Coding: 61.0Gemini 3 Pro, Agents & tools: 59.4Gemini 3 Pro, Maths: 63.1Gemini 3 Pro, Knowledge: 60.0Gemini 3 Pro, Instruction following: 69.3Gemini 3 Pro, Long context: 62.6Qwen3.7 Max, Coding: 58.6Qwen3.7 Max, Agents & tools: 48.6Qwen3.7 Max, Maths: 57.5Qwen3.7 Max, Knowledge: 60.9Qwen3.7 Max, Instruction following: 78.1Qwen3.7 Max, Long context: 64.1

Not drawn, measured for fewer than two of these models: Reasoning, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 17 benchmarks both have, Gemini 3 Pro leads 4, Qwen3.7 Max leads 13. Every overall index that rates both puts Gemini 3 Pro ahead.

Overall indexGemini 3 Pro (high)Qwen3.7 MaxLeader
BenchLeader Index60.059.8neck and neck
Arena Text1486†1474Gemini 3 Pro

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 Pro (high)Qwen3.7 Max
Blended price per 1M tokens$4.50$3.75
Input / output per 1M$2.00 / $12.00$2.50 / $7.50
Cached input per 1M–$0.500
Price per task: chat reply$0.0044$0.0033
Price per task: summarize a 30-page report$0.031$0.035
Price per task: code edit$0.030$0.026
Price per task: agentic coding session$0.168$0.180
Price per task: structured extraction$0.0064$0.0065
Agentic coding session, input mostly cached–$0.090
Output speed–145 tok/s
Time to first answer–14.1 s
Time to a complete answer, last measured 13 Nov 2026–31.2 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3 Pro (high) scores 60.0; Gemini 3 Pro scores 59.8. Qwen3.7 Max scores 59.8 and takes 14 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

145 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 Pro (high)Qwen3.7 Max
BenchLeader IndexBenchLeader60.059.8
Agents & tools scoreBenchLeader59.448.6
Coding scoreBenchLeader61.058.6
Instruction following scoreBenchLeader69.378.1
Knowledge scoreBenchLeader60.060.9
Long context scoreBenchLeader62.664.1
Maths scoreBenchLeader63.157.5
Multimodal scoreBenchLeader62.2–
Human preference scoreBenchLeader–55.6
Reasoning scoreBenchLeader–64.2
Blended price $/MBenchLeader$4.50$3.75
Output speedBenchLeader–145 tok/s
Time to first answerBenchLeader–14.1 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub92.6%†90.9%
Humanity's Last ExamScale AI / CAIS37.5%†–
SimpleBenchSimpleBench76.4%†70.4%
Arena Hard PromptsArena (LMArena)1502†1494
LiveBench 1.0 ReasoningLiveBench–83.3%
GPQA Diamond (AA)Artificial Analysis90.8%92.3%
Humanity's Last Exam (AA)Artificial Analysis39.7%40.5%
GPQA Diamond (Vals)Vals AI91.7%90.2%
Kagi LLM BenchmarkKagi LLM Benchmark80.1%†–
GPQA Diamond (HELM)HELM Capabilities80.3%†–
ARC-AGI-1ARC Prize75.0%†–
ARC-AGI-2ARC Prize31.1%†–
CritPtArtificial Analysis9.1%13.4%
SciPredictScale AI SEAL25.3%†–
Arena ExpertArena (LMArena)1498†1508
Chess PuzzlesEpoch AI Benchmarking Hub–27.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–32.0%
CL-benchEpoch AI Benchmarking Hub15.8%†–
LMCAEpoch AI Benchmarking Hub–44.0%
DTBenchEpoch AI Benchmarking Hub–92.3%
ForecastBenchForecastBench64.8%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub72.9%†77.3%
SciCodeSciCode–49.5%
WeirdMLWeirdML69.9%†–
GSO-BenchGSO-Bench18.6%†–
Show all 145 benchmarks
MetricPublisherGemini 3 Pro (high)Qwen3.7 Max
Coding
Arena CodingArena (LMArena)1517†1524
Arena WebDevArena (LMArena)1441†1516
LiveBench 1.0 CodingLiveBench–74.2%
LiveCodeBenchVals AI86.4%†87.1%
SWE-bench (Vals)Vals AI76.4%68.8%
SWE-Bench ProScale AI SEAL43.3%†–
SWE-bench Verified (bash only)SWE-bench69.6%–
SWE-bench Multilingual (bash only)SWE-bench68.7%†–
SWE-bench Verified (any scaffold)SWE-bench77.4%†–
Code MigrationVals AI–13.1%
Vibe Code Bench v1.1Vals AI14.3%47.7%
SWE-Bench Pro (private)Scale AI SEAL17.9%†–
ALE-BenchEpoch AI Benchmarking Hub1176.8†1189.4
AlgoTuneAlgoTune1.8†–
Terminal-Bench 4.0 (AA)Artificial Analysis–1.5%
Terminal-Bench 2.1 (AA)Artificial Analysis–74.5%
Startrise FrontendStartrise–63.6%
LiveCodeBench (AA)Artificial Analysis91.8%–
Agents & tools
Terminal-BenchTerminal-Bench69.4%†–
GDPvalOpenAI40.3%†–
Remote Labor IndexScale AI / CAIS1.3%†–
Arena AgentArena (LMArena)–-8.3
LiveBench Agentic CodingLiveBench–43.6%
Terminal-Bench HardArtificial Analysis41.7%50.8%
τ²-Bench Telecom (AA)Artificial Analysis87.1%94.7%
Terminal-Bench 2.1 (Vals)Vals AI–61.0%
MCP AtlasScale AI SEAL70.3%†–
BFCL OverallBerkeley Function Calling Leaderboard72.5%†–
τ²-benchτ²-bench82.5%–
τ³-bench Bankingτ²-bench18.0%–
GDPval-AA v2.1Artificial Analysis–1134
τ³-Banking (AA)Artificial Analysis–11.8%
ITBench SRE (AA)Artificial Analysis–42.5%
Analyst Agent (AA)Artificial Analysis–18.8%
Finance Agent v2Vals AI–47.8%
Harvey's Legal Agent Benchmark v1Vals AI–1.7%
Legal Research BenchVals AI–25.5%
Poker AgentVals AI1079†–
Tax Agent BenchVals AI–15.8%
Terminal-Bench 2.0 (Vals)Vals AI55.1%59.2%
Arena SearchArena (LMArena)1201†–
Arena Agent Task CompletionArena (LMArena)–-10.6
BALROGBALROG58.1%†–
DeepResearch BenchDeepResearch Bench46.3%†–
METR Time HorizonsMETR71.0%†–
GBAEvalEpoch AI Benchmarking Hub–0.4%
Vending-Bench 2Andon Labs5478.2†–
AutomationBenchArtificial Analysis–23.0%
GDP.pdf (AA)Artificial Analysis–8.6%
EnterpriseOps-GymArtificial Analysis–45.0%
AA-Briefcase v1.1Artificial Analysis–917
Design Arena AgenticDesign Arena1072†1171
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–64.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub–34.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub91.4%†95.6%
ProofBenchVals AI20.0%†26.0%
LiveBench MathematicsLiveBench–85.3%
AIME (Vals)Vals AI96.7%–
MGSMVals AI93.9%–
AIME 2026MathArena91.7%†–
HMMT February 2026MathArena86.4%†–
MathArena ApexMathArena23.4%†–
Omni-MATH (HELM)HELM Capabilities55.6%†–
MATH 500Vals AI96.4%–
Arena MathsArena (LMArena)1475†1481
AIME 2025 (AA)Artificial Analysis95.7%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–55.8%
LiveBench 1.0 Data AnalysisLiveBench–71.8%
MMLU-ProVals AI90.1%†89.3%
LegalBenchVals AI87.0%84.9%
CorpFinVals AI63.7%63.7%
TaxEvalVals AI72.6%75.3%
MedQAVals AI96.0%–
PRBench FinanceScale AI SEAL39.2%†–
PRBench LegalScale AI SEAL40.6%†–
MultiNRCScale AI SEAL59.0%†–
MMLU-Pro (HELM)HELM Capabilities90.3%†–
CaseLaw v2Vals AI53.1%–
Excel Modeling BenchmarkVals AI–57.0%
MedCodeVals AI52.2%38.8%
MedScribeVals AI72.0%79.4%
DrugDiscoveryBenchScale AI SEAL–29.3%†
EBR-benchEpoch AI Benchmarking Hub–9.5%
Global-MMLU-Lite (AA)Artificial Analysis92.2%–
Instruction following
LiveBench LanguageLiveBench–79.7%
LiveBench Instruction FollowingLiveBench–74.0%
IFBenchArtificial Analysis70.4%80.5%
MultiChallengeScale AI SEAL65.7%†–
TutorBenchScale AI SEAL53.7%†–
IFEval (HELM)HELM Capabilities87.6%†–
WildBench (HELM)HELM Capabilities85.9%†–
Arena Instruction FollowingArena (LMArena)1473†1466
Human preference
Arena TextArena (LMArena)1486†1474
EQ-Bench 4EQ-Bench–1100
EQ-Bench Creative Writing v3EQ-Bench1524†–
Arena Creative WritingArena (LMArena)1484†1440
Arena Multi-turnArena (LMArena)1496†1481
Arena Longer QueriesArena (LMArena)1491†1491
Multimodal
Arena VisionArena (LMArena)1305†–
MMMU-ProArtificial Analysis80.2%–
VISTAScale AI SEAL51.5%†–
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI69.1%–
AudioMCScale AI SEAL54.6%†–
AudioMC (text output)Scale AI SEAL54.6%†–
VTBScale AI SEAL26.9%†–
GeoBenchGeoBench84.0%†–
VPCTEpoch AI Benchmarking Hub91.0%†–
Long context
AA-LCR v1.1Artificial Analysis76.0%79.0%
Arena DocumentArena (LMArena)1451†–
MLCRArtificial Analysis–14.4%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub153.0†154.6
LiveBench 1.0LiveBench–73.1%
AA Intelligence Index v4.3.2Artificial Analysis28.029.5
AA Progress Index v1Artificial Analysis290.7293.8
HELM Capabilities meanHELM Capabilities79.9%†–
Safety & honesty
FORTRESSScale AI SEAL41.7%†–
MASKScale AI SEAL42.6%†–
PropensityBenchScale AI SEAL52.9%†–
Metadata
AA Openness IndexArtificial Analysis5.6–

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

What changed

  • Qwen3.7 Max: BenchLeader Index 60.3 → 59.8.
  • Qwen3.7 Max: 1 score revision.
  • Gemini 3 Pro (high): 1 new result (AIME 2025 (AA)).
  • Gemini 3 Pro (high): BenchLeader Index 60.5 → 60.0.
  • Qwen3.7 Max: BenchLeader Index 60.8 → 60.3.
  • Gemini 3 Pro (high): 1 new result (AA Progress Index v1).
  • Gemini 3 Pro (high): BenchLeader Index 61.0 → 60.5.

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

Gemini 3 Pro vs Qwen3.7 Max: questions

Is Gemini 3 Pro better than Qwen3.7 Max?
Gemini 3 Pro (high) and Qwen3.7 Max are neck and neck on quality (60.0 vs 59.8, within the ±5.0 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 19 Nov 2026, so check the category scores for your use.
Gemini 3 Pro vs Qwen3.7 Max: which is cheaper, and will that change?
Qwen3.7 Max is cheaper today: $3.75 against $4.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 3 Pro or Qwen3.7 Max better for coding?
Gemini 3 Pro scores higher in coding (61 vs 59 on the category index, where 50 is average).
Is Gemini 3 Pro or Qwen3.7 Max better for agents and tool use?
Gemini 3 Pro scores higher in agentic tasks (59 vs 49 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 41.7% for Gemini 3 Pro against 50.8% for Qwen3.7 Max.
Which is better for long documents?
Qwen3.7 Max scores higher on long-context benchmarks (64 vs 63). Both accept 1,000,000 tokens of context.
More questions (2)
Do independent benchmarks agree on Gemini 3 Pro vs Qwen3.7 Max?
Across the 17 benchmarks both have, Gemini 3 Pro leads 4, Qwen3.7 Max leads 13. Every overall index that rates both puts Gemini 3 Pro ahead.
When was Qwen3.7 Max released?
Qwen3.7 Max was released on 19 May 2026.