Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.5-27B vs Qwen3.7 Plus

Data verified

Head-to-head evidence from 21 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

60.7/100
Margin
6.5pts
winning →
67.22/100
2 category wins4 category wins

Public leaderboard positions: Qwen3.5-27B #45 (Supported); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5-27B and Qwen3.7 Plus share 21 comparable benchmark results. 6 of 8 categories are comparable. 7 results are unique to Qwen3.5-27B; 48 to Qwen3.7 Plus.

Updated July 23, 2026
Shared results
21
Qwen3.5-27B only
7
Qwen3.7 Plus only
48
Comparable categories
6 / 8

Pick Qwen3.7 Plus if you want the stronger benchmark profile. Qwen3.5-27B only becomes the better choice if knowledge is the priority.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 7 evidence categories; 6 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 Plus is clearly ahead on the BenchAlign aggregate, 67.22 to 60.7. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.7 Plus's sharpest advantage is in reasoning, where it averages 91.7 against 60.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 41.6% to 70.3%. Qwen3.5-27B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Qwen3.7 Plus gives you the larger context window at 1M, compared with 262K for Qwen3.5-27B.

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 Qwen3.5-27B and Qwen3.7 Plus
CategoryQwen3.5-27BΔQwen3.7 Plus
ReasoningQwen3.5-27B60.6Margin→ 31.1Qwen3.7 Plus91.7
KnowledgeQwen3.5-27B82.7Margin← 22.6Qwen3.7 Plus60.1
AgenticQwen3.5-27B52.0Margin→ 19.7Qwen3.7 Plus71.7
CodingQwen3.5-27B64.9Margin→ 10.7Qwen3.7 Plus75.6
Inst. FollowingQwen3.5-27B95.0Margin← 10.5Qwen3.7 Plus84.5
MultilingualQwen3.5-27B82.2Margin→ 3.2Qwen3.7 Plus85.4
MathQwen3.5-27BNot measuredMarginNo overlapQwen3.7 Plus92.9
MultimodalQwen3.5-27BNot measuredMarginNo overlapQwen3.7 Plus81.5

Decisive benchmark drivers

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

More
A · Qwen3.5-27BB · Qwen3.7 Plus

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 41.6%B 70.3%
    Winner: Qwen3.7 PlusΔ 28.7
    Terminal-Bench 2.0: Qwen3.5-27B scored 41.6%; Qwen3.7 Plus scored 70.3%. Qwen3.7 Plus wins this benchmark.

  2. OSWorld-Verified

    Agentic
    Source ↗
    A 56.2%B 73.3%
    Winner: Qwen3.7 PlusΔ 17.1
    OSWorld-Verified: Qwen3.5-27B scored 56.2%; Qwen3.7 Plus scored 73.3%. Qwen3.7 Plus wins this benchmark.

  3. SuperGPQA

    Knowledge
    Source ↗
    A 65.6%B 71.4%
    Winner: Qwen3.7 PlusΔ 5.8
    SuperGPQA: Qwen3.5-27B scored 65.6%; Qwen3.7 Plus scored 71.4%. Qwen3.7 Plus wins this benchmark.

  4. SWE-bench Verified

    Coding
    Source ↗
    A 72.4%B 77.7%
    Winner: Qwen3.7 PlusΔ 5.3
    SWE-bench Verified: Qwen3.5-27B scored 72.4%; Qwen3.7 Plus scored 77.7%. Qwen3.7 Plus wins this benchmark.

  5. GPQA

    Knowledge
    Source ↗
    A 85.5%B 90.3%
    Winner: Qwen3.7 PlusΔ 4.8
    GPQA: Qwen3.5-27B scored 85.5%; Qwen3.7 Plus scored 90.3%. Qwen3.7 Plus wins this benchmark.

Operational comparison

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

MetricQwen3.5-27BQwen3.7 PlusComparison
Input / output priceUSD per 1M tokensQwen3.5-27B$0 input / $0 outputQwen3.7 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.5-27BNot availableQwen3.7 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5-27BNot availableQwen3.7 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5-27B262KQwen3.7 Plus1MQwen3.7 Plus lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.7 Plus wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
Terminal-Bench 2.0Source 41.6%70.3%Qwen3.7 Plus leads
BrowseCompSource 61%—Not comparable
OSWorld-VerifiedSource 56.2%73.3%Qwen3.7 Plus leads
τ²-bench resultsSource 93.9%93%Qwen3.5-27B leads
Gert LabsSource 39.41%—Not comparable
QwenClawBenchSource —61.8%Not comparable
QwenWebBenchSource —1536Not comparable
Claw-EvalSource —62.7%Not comparable
BFCL v4Source —72.9%Not comparable
MCP AtlasSource —73.2%Not comparable
VITA-BenchSource —45.6%Not comparable
DeepPlanningSource —62.3%Not comparable
AndroidWorldSource —81.0%Not comparable
AA Agentic IndexSource —20.8%Not comparable
APEX-Agents-AASource —22.4%Not comparable
GDPval-AASource —21.8%Not comparable
GDPval-AASource —936Not comparable
OSWorld 2.0Source —2.8%Not comparable
CodingQwen3.7 Plus wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
SWE-bench VerifiedSource 72.4%77.7%Qwen3.7 Plus leads
SWE-RebenchSource 58.9%—Not comparable
AA-SciCodeSource 39.5%45.5%Qwen3.7 Plus leads
Terminal-Bench 2.0Source —70.3%Not comparable
SWE-bench ProSource —57.6%Not comparable
SWE MultilingualSource —75.8%Not comparable
NL2RepoSource —41.1%Not comparable
SciCodeSource —51.3%Not comparable
LiveCodeBenchSource —89.6%Not comparable
AA Coding IndexSource —55.9%Not comparable
ReasoningQwen3.7 Plus wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
LongBench v2Source 60.6%—Not comparable
AA-LCRSource 67.3%65.0%Qwen3.5-27B leads
CritPtSource 0.9%9.1%Qwen3.7 Plus leads
MRCRv2Source —91.7%Not comparable
KnowledgeQwen3.5-27B wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
MMLU-ProSource 86.1%88.5%Qwen3.7 Plus leads
SuperGPQASource 65.6%71.4%Qwen3.7 Plus leads
GPQASource 85.5%90.3%Qwen3.7 Plus leads
Artificial Analysis Intelligence IndexSource 33.8%39.0%Qwen3.7 Plus leads
AA-GPQA DiamondSource 85.8%90.0%Qwen3.7 Plus leads
AA-HLESource 22.2%33.4%Qwen3.7 Plus leads
AA-Omniscience IndexSource -42.0%2.4%Qwen3.7 Plus leads
AA-Omniscience AccuracySource 21.0%22.2%Qwen3.7 Plus leads
AA-Omniscience Hallucination RateSource 79.7%25.5%Qwen3.7 Plus leads
GPQA-DSource —90.3%Not comparable
HLESource —34.7%Not comparable
MMLU-ReduxSource —94.5%Not comparable
MMMLUSource —89.0%Not comparable
Math
BenchmarkQwen3.5-27BQwen3.7 PlusResult
HMMT Feb 2026Source —92.9%Not comparable
IMOAnswerBenchSource —86.0%Not comparable
ApexSource —22.7%Not comparable
MultilingualQwen3.7 Plus wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
MMLU-ProXSource 82.2%85.4%Qwen3.7 Plus leads
NOVA-63Source —58.8%Not comparable
INCLUDESource —83.0%Not comparable
MAXIFESource —88.8%Not comparable
PolyMathSource —84.0%Not comparable
Multimodal
BenchmarkQwen3.5-27BQwen3.7 PlusResult
MMMUSource 82.3%—Not comparable
MMVUSource 73.3%—Not comparable
MathVisionSource 86.0%90.3%Qwen3.7 Plus leads
V*Source 93.7%—Not comparable
AA-MMMU-ProSource 75.0%80.5%Qwen3.7 Plus leads
MMMU-ProSource —79%Not comparable
CharXivSource —85.9%Not comparable
ERQASource —69.8%Not comparable
MedXpertQA (MM)Source —71.0%Not comparable
ScreenSpot ProSource —79.0%Not comparable
SimpleVQASource —81.7%Not comparable
MMSearch-PlusSource —41.4%Not comparable
RealWorldQASource —86.9%Not comparable
OmniDocBench 1.5Source —91.4%Not comparable
OCRBench V2Source —70.7%Not comparable
ODINW13Source —51.1%Not comparable
Video-MME (with subtitle)Source —88.0%Not comparable
VideoMMMUSource —85.4%Not comparable
MLVU (M-Avg)Source —87.4%Not comparable
Design Arena WebsiteSource —1288Not comparable
Inst. FollowingQwen3.5-27B wins
BenchmarkQwen3.5-27BQwen3.7 PlusResult
IFEvalSource 95%94.6%Qwen3.5-27B leads
AA-IFBenchSource 75.6%78.0%Qwen3.7 Plus leads
IFBenchSource —79.1%Not comparable
Frequently Asked Questions (7)

Which is better, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.7 Plus is ahead on BenchLM's BenchAlign leaderboard, 67.22 to 60.7. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 41.6% and 70.3%.

Which is better for knowledge tasks, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.5-27B has the edge for knowledge tasks in this comparison, averaging 82.7 versus 60.1. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for coding in this comparison, averaging 75.6 versus 64.9. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for reasoning in this comparison, averaging 91.7 versus 60.6. Inside this category, CritPt is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for agentic tasks in this comparison, averaging 71.7 versus 52. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.5-27B has the edge for instruction following in this comparison, averaging 95 versus 84.5. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3.5-27B or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for multilingual tasks in this comparison, averaging 85.4 versus 82.2. 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.