Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.5 397B vs Qwen3.7 Max

Data verified

Head-to-head evidence from 33 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

57.01/100
Margin
15.8pts
winning →
72.84/100
1 category wins6 category wins

Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5 397B and Qwen3.7 Max share 33 comparable benchmark results. 7 of 8 categories are comparable. 22 results are unique to Qwen3.5 397B; 25 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
33
Qwen3.5 397B only
22
Qwen3.7 Max only
25
Comparable categories
7 / 8

Pick Qwen3.7 Max if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 33 shared benchmark results across 7 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 57.01. 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 reasoning, where it averages 90.4 against 63.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 52.5% to 69.7%. Qwen3.5 397B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.

Qwen3.7 Max is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.7 Max gives you the larger context window at 1M, compared with 128K for Qwen3.5 397B.

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 Qwen3.5 397B and Qwen3.7 Max
CategoryQwen3.5 397BΔQwen3.7 Max
ReasoningQwen3.5 397B63.2Margin→ 27.2Qwen3.7 Max90.4
AgenticQwen3.5 397B56.5Margin→ 13.2Qwen3.7 Max69.7
CodingQwen3.5 397B66.5Margin→ 11.4Qwen3.7 Max77.9
Inst. FollowingQwen3.5 397B92.6Margin← 8.2Qwen3.7 Max84.4
KnowledgeQwen3.5 397B56.6Margin→ 7.6Qwen3.7 Max64.2
MathQwen3.5 397B90.6Margin→ 6.5Qwen3.7 Max97.1
MultilingualQwen3.5 397B84.7Margin→ 2.3Qwen3.7 Max87.0
MultimodalQwen3.5 397B79.6MarginNo overlapQwen3.7 MaxNot measured

Decisive benchmark drivers

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

More
A · Qwen3.5 397BB · Qwen3.7 Max

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 52.5%B 69.7%
    Winner: Qwen3.7 MaxΔ 17.2
    Terminal-Bench 2.0: Qwen3.5 397B scored 52.5%; Qwen3.7 Max scored 69.7%. Qwen3.7 Max wins this benchmark.

  2. HLE

    Knowledge
    Source ↗
    A 28.7%B 41.4%
    Winner: Qwen3.7 MaxΔ 12.7
    HLE: Qwen3.5 397B scored 28.7%; Qwen3.7 Max scored 41.4%. Qwen3.7 Max wins this benchmark.

  3. SWE-bench Pro

    Coding
    Source ↗
    A 50.9%B 60.6%
    Winner: Qwen3.7 MaxΔ 9.7
    SWE-bench Pro: Qwen3.5 397B scored 50.9%; Qwen3.7 Max scored 60.6%. Qwen3.7 Max wins this benchmark.

  4. HMMT Feb 2026

    Math
    Source ↗
    A 87.9%B 97.1%
    Winner: Qwen3.7 MaxΔ 9.2
    HMMT Feb 2026: Qwen3.5 397B scored 87.9%; Qwen3.7 Max scored 97.1%. Qwen3.7 Max wins this benchmark.

  5. SWE-bench Verified

    Coding
    Source ↗
    A 76.2%B 80.4%
    Winner: Qwen3.7 MaxΔ 4.2
    SWE-bench Verified: Qwen3.5 397B scored 76.2%; Qwen3.7 Max scored 80.4%. Qwen3.7 Max wins this benchmark.

Operational comparison

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

MetricQwen3.5 397BQwen3.7 MaxComparison
Input / output priceUSD per 1M tokensQwen3.5 397B$0.6 input / $3.6 outputQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.5 397B96 tok/sQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5 397B2.44 sQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5 397B128KQwen3.7 Max1MQwen3.7 Max lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.7 Max wins
BenchmarkQwen3.5 397BQwen3.7 MaxResult
Terminal-Bench 2.0Source 52.5%69.7%Qwen3.7 Max leads
BrowseCompSource 62%—Not comparable
Claw-EvalSource 56.8%65.2%Qwen3.7 Max leads
QwenClawBenchSource 51.8%64.3%Qwen3.7 Max leads
τ³-bench resultsSource 68.4%—Not comparable
VITA-BenchSource 43.7%47.9%Qwen3.7 Max leads
DeepPlanningSource 37.6%—Not comparable
ToolathlonSource 36.3%—Not comparable
MCP AtlasSource 46.1%76.4%Qwen3.7 Max leads
MCP-TasksSource 74.2%—Not comparable
WideResearchSource 74.0%—Not comparable
τ²-bench resultsSource 95.6%94.7%Qwen3.5 397B leads
Gert LabsSource 46.76%64.27%Qwen3.7 Max leads
ResearchClawBenchSource 14.2%18.7%Qwen3.7 Max leads
AA Agentic IndexSource 19.9%30.6%Qwen3.7 Max leads
APEX-Agents-AASource 15.3%—Not comparable
GDPval-AASource 23.1%38.7%Qwen3.7 Max leads
GDPval-AASource 9621273Qwen3.7 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
BenchmarkQwen3.5 397BQwen3.7 MaxResult
SWE-bench VerifiedSource 76.2%80.4%Qwen3.7 Max leads
LiveCodeBench v6Source 83.6%—Not comparable
SWE-bench ProSource 50.9%60.6%Qwen3.7 Max leads
AA-SciCodeSource 42.0%48.8%Qwen3.7 Max leads
AA Coding IndexSource 48.2%66.0%Qwen3.7 Max leads
SWE MultilingualSource —78.3%Not comparable
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
BenchmarkQwen3.5 397BQwen3.7 MaxResult
LongBench v2Source 63.2%—Not comparable
AI-NeedleSource 68.7%—Not comparable
AA-LCRSource 65.7%69.0%Qwen3.7 Max leads
CritPtSource 1.7%13.4%Qwen3.7 Max leads
MRCRv2Source —90.4%Not comparable
KnowledgeQwen3.7 Max wins
BenchmarkQwen3.5 397BQwen3.7 MaxResult
GPQASource 88.4%92.4%Qwen3.7 Max leads
SuperGPQASource 70.4%73.6%Qwen3.7 Max leads
MMLU-ProSource 87.8%89.6%Qwen3.7 Max leads
MMLU-ReduxSource 94.9%95%Qwen3.7 Max leads
C-EvalSource 93%—Not comparable
HLESource 28.7%41.4%Qwen3.7 Max leads
Artificial Analysis Intelligence IndexSource 33.7%46.0%Qwen3.7 Max leads
AA-GPQA DiamondSource 89.3%92.3%Qwen3.7 Max leads
AA-HLESource 27.3%38.1%Qwen3.7 Max leads
AA-Omniscience IndexSource -29.8%14.1%Qwen3.7 Max leads
AA-Omniscience AccuracySource 31.4%30.1%Qwen3.5 397B leads
AA-Omniscience Hallucination RateSource 89.1%22.9%Qwen3.7 Max leads
GPQA-DSource —92.4%Not comparable
MMMLUSource —90.3%Not comparable
MathQwen3.7 Max wins
BenchmarkQwen3.5 397BQwen3.7 MaxResult
AIME26Source 93.3%—Not comparable
HMMT Feb 2025Source 94.8%—Not comparable
HMMT Nov 2025Source 92.7%—Not comparable
HMMT Feb 2026Source 87.9%97.1%Qwen3.7 Max leads
MMAnswerBenchSource 80.9%—Not comparable
IMOAnswerBenchSource —90.0%Not comparable
ApexSource —44.5%Not comparable
MultilingualQwen3.7 Max wins
BenchmarkQwen3.5 397BQwen3.7 MaxResult
MMLU-ProXSource 84.7%87%Qwen3.7 Max leads
NOVA-63Source 59.1%59.0%Qwen3.5 397B leads
INCLUDESource —86.2%Not comparable
MAXIFESource —89.2%Not comparable
PolyMathSource —86.5%Not comparable
Multimodal
BenchmarkQwen3.5 397BQwen3.7 MaxResult
MMMU-ProSource 79%—Not comparable
MathVisionSource 88.6%—Not comparable
CharXivSource 80.8%—Not comparable
VideoMMMUSource 84.7%—Not comparable
ScreenSpot ProSource 65.6%—Not comparable
V*Source 95.8%—Not comparable
AA-MMMU-ProSource 77.3%—Not comparable
Design Arena WebsiteSource —1293Not comparable
Inst. FollowingQwen3.5 397B wins
BenchmarkQwen3.5 397BQwen3.7 MaxResult
IFEvalSource 92.6%94.3%Qwen3.7 Max leads
AA-IFBenchSource 78.8%80.5%Qwen3.7 Max leads
IFBenchSource —79.1%Not comparable
Frequently Asked Questions (8)

Which is better, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max is ahead on BenchLM's BenchAlign leaderboard, 72.84 to 57.01. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 52.5% and 69.7%.

Which is better for knowledge tasks, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max has the edge for knowledge tasks in this comparison, averaging 64.2 versus 56.6. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max has the edge for coding in this comparison, averaging 77.9 versus 66.5. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max has the edge for math in this comparison, averaging 97.1 versus 90.6. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max has the edge for reasoning in this comparison, averaging 90.4 versus 63.2. Inside this category, CritPt is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.7 Max has the edge for agentic tasks in this comparison, averaging 69.7 versus 56.5. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3.5 397B or Qwen3.7 Max?

Qwen3.5 397B has the edge for instruction following in this comparison, averaging 92.6 versus 84.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3.5 397B 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.