Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.6 Plus vs Qwen3.7 Max

Data verified

Head-to-head evidence from 36 shared benchmark results across 8 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.2/100
Margin
7.6pts
winning →
72.84/100
0 category wins7 category wins

Public leaderboard positions: Qwen3.6 Plus #30 (Supported); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.6 Plus and Qwen3.7 Max share 36 comparable benchmark results. 7 of 8 categories are comparable. 24 results are unique to Qwen3.6 Plus; 22 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
36
Qwen3.6 Plus only
24
Qwen3.7 Max only
22
Comparable categories
7 / 8

Pick Qwen3.7 Max if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Confidence note. This is a partial-evidence comparison with 36 shared benchmark results across 8 evidence categories; 7 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.7 Max is clearly ahead on the BenchAlign aggregate, 72.84 to 65.2. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.7 Max's sharpest advantage is in mathematics, where it averages 97.1 against 60.5. The single biggest benchmark swing on the page is HLE, 28.8% to 41.4%.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Qwen3.6 Plus and Qwen3.7 Max
CategoryQwen3.6 PlusΔQwen3.7 Max
MathQwen3.6 Plus60.5Margin→ 36.6Qwen3.7 Max97.1
ReasoningQwen3.6 Plus62.0Margin→ 28.4Qwen3.7 Max90.4
AgenticQwen3.6 Plus61.6Margin→ 8.1Qwen3.7 Max69.7
CodingQwen3.6 Plus70.3Margin→ 7.6Qwen3.7 Max77.9
KnowledgeQwen3.6 Plus57.1Margin→ 7.1Qwen3.7 Max64.2
MultilingualQwen3.6 Plus84.7Margin→ 2.3Qwen3.7 Max87.0
Inst. FollowingQwen3.6 Plus82.3Margin→ 2.1Qwen3.7 Max84.4
MultimodalQwen3.6 Plus79.8MarginNo overlapQwen3.7 MaxNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Qwen3.6 PlusB · Qwen3.7 Max

  1. HLE

    Knowledge
    Source ↗
    A 28.8%B 41.4%
    Winner: Qwen3.7 MaxΔ 12.6
    HLE: Qwen3.6 Plus scored 28.8%; Qwen3.7 Max scored 41.4%. Qwen3.7 Max wins this benchmark.

  2. HMMT Feb 2026

    Math
    Source ↗
    A 87.8%B 97.1%
    Winner: Qwen3.7 MaxΔ 9.3
    HMMT Feb 2026: Qwen3.6 Plus scored 87.8%; Qwen3.7 Max scored 97.1%. Qwen3.7 Max wins this benchmark.

  3. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 61.6%B 69.7%
    Winner: Qwen3.7 MaxΔ 8.1
    Terminal-Bench 2.0: Qwen3.6 Plus scored 61.6%; Qwen3.7 Max scored 69.7%. Qwen3.7 Max wins this benchmark.

  4. SWE-bench Pro

    Coding
    Source ↗
    A 56.6%B 60.6%
    Winner: Qwen3.7 MaxΔ 4
    SWE-bench Pro: Qwen3.6 Plus scored 56.6%; Qwen3.7 Max scored 60.6%. Qwen3.7 Max wins this benchmark.

  5. IFBench

    Inst. Following
    Source ↗
    A 75.8%B 79.1%
    Winner: Qwen3.7 MaxΔ 3.3
    IFBench: Qwen3.6 Plus scored 75.8%; Qwen3.7 Max scored 79.1%. Qwen3.7 Max wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricQwen3.6 PlusQwen3.7 MaxComparison
Input / output priceUSD per 1M tokensQwen3.6 PlusNot availableQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.6 PlusNot availableQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.6 PlusNot availableQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.6 Plus1MQwen3.7 Max1MListed context windows are equal.

Benchmark Deep Dive

AgenticQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
Terminal-Bench 2.0Source 61.6%69.7%Qwen3.7 Max leads
Claw-EvalSource 58.8%65.2%Qwen3.7 Max leads
QwenClawBenchSource 57.2%64.3%Qwen3.7 Max leads
τ³-bench resultsSource 70.7%—Not comparable
VITA-BenchSource 44.3%47.9%Qwen3.7 Max leads
DeepPlanningSource 41.5%—Not comparable
ToolathlonSource 39.8%—Not comparable
MCP AtlasSource 48.2%76.4%Qwen3.7 Max leads
MCP-TasksSource 74.1%—Not comparable
WideResearchSource 74.3%—Not comparable
AA Agentic IndexSource 27.6%30.6%Qwen3.7 Max leads
τ²-bench resultsSource 97.7%94.7%Qwen3.6 Plus leads
GDPval-AASource 31.8%38.7%Qwen3.7 Max leads
GDPval-AASource 11351273Qwen3.7 Max leads
Gert LabsSource 50.60%64.27%Qwen3.7 Max leads
ResearchClawBenchSource 18.0%18.7%Qwen3.7 Max leads
QwenWebBenchSource —1568Not comparable
BFCL v4Source —75.0%Not comparable
HLE w/ toolsSource —53.5%Not comparable
AA BriefcaseSource —908Not comparable
AA AutomationBenchSource —25.6%Not comparable
AA EnterpriseOps-GymSource —45.0%Not comparable
AA ITBenchSource —42.5%Not comparable
terminalBenchHardSource —50.8%Not comparable
aaTerminalBench21Source —74.5%Not comparable
AA Harvey LABSource —83.4%Not comparable
CodingQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
SWE-bench VerifiedSource 78.8%80.4%Qwen3.7 Max leads
SWE-bench ProSource 56.6%60.6%Qwen3.7 Max leads
SWE MultilingualSource 73.8%78.3%Qwen3.7 Max leads
LiveCodeBench v6Source 87.1%—Not comparable
Vibe Code BenchSource 25.56%—Not comparable
AA Coding IndexSource 54.5%66.0%Qwen3.7 Max leads
AA-SciCodeSource 40.7%48.8%Qwen3.7 Max leads
NL2RepoSource —47.2%Not comparable
SciCodeSource —53.5%Not comparable
LiveCodeBenchSource —91.6%Not comparable
Terminal-Bench 2.0Source —69.7%Not comparable
ReasoningQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
AI-NeedleSource 68.3%—Not comparable
LongBench v2Source 62%—Not comparable
AA-LCRSource 69.7%69.0%Qwen3.6 Plus leads
CritPtSource 2.9%13.4%Qwen3.7 Max leads
MRCRv2Source —90.4%Not comparable
KnowledgeQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
GPQASource 90.4%92.4%Qwen3.7 Max leads
SuperGPQASource 71.6%73.6%Qwen3.7 Max leads
MMLU-ProSource 88.5%89.6%Qwen3.7 Max leads
MMLU-ReduxSource 94.5%95%Qwen3.7 Max leads
C-EvalSource 93.3%—Not comparable
HLESource 28.8%41.4%Qwen3.7 Max leads
Artificial Analysis Intelligence IndexSource 39.6%46.0%Qwen3.7 Max leads
AA-GPQA DiamondSource 88.2%92.3%Qwen3.7 Max leads
AA-HLESource 25.7%38.1%Qwen3.7 Max leads
AA-Omniscience IndexSource 2.7%14.1%Qwen3.7 Max leads
AA-Omniscience AccuracySource 26.2%30.1%Qwen3.7 Max leads
AA-Omniscience Hallucination RateSource 32.0%22.9%Qwen3.7 Max leads
GPQA-DSource —92.4%Not comparable
MMMLUSource —90.3%Not comparable
MathQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
AIME26Source 95.3%—Not comparable
HMMT Feb 2025Source 96.7%—Not comparable
HMMT Nov 2025Source 94.6%—Not comparable
HMMT Feb 2026Source 87.8%97.1%Qwen3.7 Max leads
MMAnswerBenchSource 83.8%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 26.207%—Not comparable
FrontierMath v2 (Tier 4)Source 8.333%—Not comparable
IMOAnswerBenchSource —90.0%Not comparable
ApexSource —44.5%Not comparable
MultilingualQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
MMLU-ProXSource 84.7%87%Qwen3.7 Max leads
NOVA-63Source 57.9%59.0%Qwen3.7 Max leads
INCLUDESource —86.2%Not comparable
MAXIFESource —89.2%Not comparable
PolyMathSource —86.5%Not comparable
Multimodal
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
MMMUSource 86.0%—Not comparable
MMMU-ProSource 78.8%—Not comparable
MathVisionSource 88.0%—Not comparable
VideoMMMUSource 84.0%—Not comparable
ScreenSpot ProSource 68.2%—Not comparable
CharXivSource 81.5%—Not comparable
V*Source 96.9%—Not comparable
AA-MMMU-ProSource 78.0%—Not comparable
Design Arena WebsiteSource 12491293Qwen3.7 Max leads
Inst. FollowingQwen3.7 Max wins
BenchmarkQwen3.6 PlusQwen3.7 MaxResult
IFEvalSource 94.3%94.3%Tie
IFBenchSource 75.8%79.1%Qwen3.7 Max leads
AA-IFBenchSource 75.2%80.5%Qwen3.7 Max leads
Frequently Asked Questions (8)

Which is better, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max is ahead on BenchLM's BenchAlign leaderboard, 72.84 to 65.2. The biggest single separator in this matchup is HLE, where the scores are 28.8% and 41.4%.

Which is better for knowledge tasks, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for knowledge tasks in this comparison, averaging 64.2 versus 57.1. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for coding in this comparison, averaging 77.9 versus 70.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for math in this comparison, averaging 97.1 versus 60.5. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for reasoning in this comparison, averaging 90.4 versus 62. Inside this category, CritPt is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for agentic tasks in this comparison, averaging 69.7 versus 61.6. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for instruction following in this comparison, averaging 84.4 versus 82.3. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3.6 Plus or Qwen3.7 Max?

Qwen3.7 Max has the edge for multilingual tasks in this comparison, averaging 87 versus 84.7. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Alibaba Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.