Skip to main content

Model comparison

Qwen3.6-35B-A3B vs Qwen3.6 Plus

Data verified

Head-to-head evidence from 44 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

51.36/100
Margin
13.7pts
winning →
65.05/100
2 category wins3 category wins

Verified leaderboard positions: Qwen3.6-35B-A3B #31; Qwen3.6 Plus #14

BenchAlign evidence: Qwen3.6-35B-A3B estimated; Qwen3.6 Plus supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.6-35B-A3B and Qwen3.6 Plus share 44 comparable benchmark results. 5 of 8 categories are comparable. 14 results are unique to Qwen3.6-35B-A3B; 17 to Qwen3.6 Plus.

Updated July 15, 2026
Shared results
44
Qwen3.6-35B-A3B only
14
Qwen3.6 Plus only
17
Comparable categories
5 / 8

Pick Qwen3.6 Plus if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if mathematics is the priority.

Confidence note. This is a partial-evidence comparison with 44 shared benchmark results across 7 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.6 Plus is clearly ahead on the provisional aggregate, 63 to 59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.6 Plus's sharpest advantage is in agentic, where it averages 61.6 against 51.5. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 51.5% to 61.6%. Qwen3.6-35B-A3B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Qwen3.6 Plus gives you the larger context window at 1M, compared with 262K for Qwen3.6-35B-A3B.

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 Qwen3.6-35B-A3B and Qwen3.6 Plus
CategoryQwen3.6-35B-A3BΔQwen3.6 Plus
MathQwen3.6-35B-A3B88.2Margin 27.7Qwen3.6 Plus60.5
AgenticQwen3.6-35B-A3B51.5Margin 10.1Qwen3.6 Plus61.6
KnowledgeQwen3.6-35B-A3B51.8Margin 5.7Qwen3.6 Plus57.5
CodingQwen3.6-35B-A3B73.8Margin 3.5Qwen3.6 Plus70.3
MultimodalQwen3.6-35B-A3B76.3Margin 3.5Qwen3.6 Plus79.8
ReasoningQwen3.6-35B-A3BNot measuredMarginNo overlapQwen3.6 Plus62.0
MultilingualQwen3.6-35B-A3BNot measuredMarginNo overlapQwen3.6 Plus84.7
Inst. FollowingQwen3.6-35B-A3BNot measuredMarginNo overlapQwen3.6 Plus82.3

Decisive benchmark drivers

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

More
A · Qwen3.6-35B-A3BB · Qwen3.6 Plus
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 51.5%B 61.6%
    Winner: Qwen3.6 PlusΔ 10.1
    Terminal-Bench 2.0: Qwen3.6-35B-A3B scored 51.5%; Qwen3.6 Plus scored 61.6%. Qwen3.6 Plus wins this benchmark.
  2. HLE

    Knowledge
    Source ↗
    A 21.4%B 28.8%
    Winner: Qwen3.6 PlusΔ 7.4
    HLE: Qwen3.6-35B-A3B scored 21.4%; Qwen3.6 Plus scored 28.8%. Qwen3.6 Plus wins this benchmark.
  3. SWE-bench Pro

    Coding
    Source ↗
    A 49.5%B 56.6%
    Winner: Qwen3.6 PlusΔ 7.1
    SWE-bench Pro: Qwen3.6-35B-A3B scored 49.5%; Qwen3.6 Plus scored 56.6%. Qwen3.6 Plus wins this benchmark.
  4. SuperGPQA

    Knowledge
    Source ↗
    A 64.7%B 71.6%
    Winner: Qwen3.6 PlusΔ 6.9
    SuperGPQA: Qwen3.6-35B-A3B scored 64.7%; Qwen3.6 Plus scored 71.6%. Qwen3.6 Plus wins this benchmark.
  5. SWE-bench Verified

    Coding
    Source ↗
    A 73.4%B 78.8%
    Winner: Qwen3.6 PlusΔ 5.4
    SWE-bench Verified: Qwen3.6-35B-A3B scored 73.4%; Qwen3.6 Plus scored 78.8%. Qwen3.6 Plus wins this benchmark.

Operational comparison

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

MetricQwen3.6-35B-A3BQwen3.6 PlusComparison
Input / output priceUSD per 1M tokensQwen3.6-35B-A3BNot availableQwen3.6 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.6-35B-A3BNot availableQwen3.6 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.6-35B-A3BNot availableQwen3.6 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.6-35B-A3B262KQwen3.6 Plus1MQwen3.6 Plus lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.6 Plus wins
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
Terminal-Bench 2.0Source 51.5%61.6%Qwen3.6 Plus leads
Claw-EvalSource 68.7%58.8%Qwen3.6-35B-A3B leads
QwenClawBenchSource 52.6%57.2%Qwen3.6 Plus leads
QwenWebBenchSource 1397Not comparable
τ³-bench resultsSource 67.2%70.7%Qwen3.6 Plus leads
VITA-BenchSource 35.6%44.3%Qwen3.6 Plus leads
DeepPlanningSource 25.9%41.5%Qwen3.6 Plus leads
ToolathlonSource 26.9%39.8%Qwen3.6 Plus leads
MCP AtlasSource 62.8%48.2%Qwen3.6-35B-A3B leads
WideResearchSource 60.1%74.3%Qwen3.6 Plus leads
AA Agentic IndexSource 21.4%27.6%Qwen3.6 Plus leads
τ²-bench resultsSource 95.3%97.7%Qwen3.6 Plus leads
GDPval-AASource 27.4%31.8%Qwen3.6 Plus leads
GDPval-AASource 10491135Qwen3.6 Plus leads
Gert LabsSource 42.65%50.60%Qwen3.6 Plus leads
MCP-TasksSource 74.1%Not comparable
ResearchClawBenchSource 18.0%Not comparable
CodingQwen3.6-35B-A3B wins
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
SWE-bench VerifiedSource 73.4%78.8%Qwen3.6 Plus leads
SWE MultilingualSource 67.2%73.8%Qwen3.6 Plus leads
SWE-bench ProSource 49.5%56.6%Qwen3.6 Plus leads
Terminal-Bench 2.0Source 51.5%Not comparable
LiveCodeBenchSource 80.4%Not comparable
NL2RepoSource 29.4%Not comparable
AA Coding IndexSource 41.9%54.5%Qwen3.6 Plus leads
Terminal-Bench HardSource 34.8%43.9%Qwen3.6 Plus leads
AA-SciCodeSource 35.8%40.7%Qwen3.6 Plus leads
LiveCodeBench v6Source 87.1%Not comparable
Vibe Code BenchSource 25.56%Not comparable
Reasoning
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
AA-LCRSource 63.7%69.7%Qwen3.6 Plus leads
CritPtSource 0.3%2.9%Qwen3.6 Plus leads
AI-NeedleSource 68.3%Not comparable
LongBench v2Source 62%Not comparable
KnowledgeQwen3.6 Plus wins
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
MMLU-ProSource 85.2%88.5%Qwen3.6 Plus leads
SuperGPQASource 64.7%71.6%Qwen3.6 Plus leads
C-EvalSource 90%93.3%Qwen3.6 Plus leads
GPQASource 86%90.4%Qwen3.6 Plus leads
HLESource 21.4%28.8%Qwen3.6 Plus leads
Artificial Analysis Intelligence IndexSource 31.6%39.6%Qwen3.6 Plus leads
AA-GPQA DiamondSource 84.1%88.2%Qwen3.6 Plus leads
AA-HLESource 20.2%25.7%Qwen3.6 Plus leads
AA-Omniscience IndexSource -21.4%2.7%Qwen3.6 Plus leads
AA-Omniscience AccuracySource 18.9%26.2%Qwen3.6 Plus leads
AA-Omniscience Hallucination RateSource 49.7%32.0%Qwen3.6 Plus leads
MMLU-ReduxSource 94.5%Not comparable
MathQwen3.6-35B-A3B wins
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
HMMT Feb 2025Source 90.7%96.7%Qwen3.6 Plus leads
HMMT Nov 2025Source 89.1%94.6%Qwen3.6 Plus leads
HMMT Feb 2026Source 83.6%87.8%Qwen3.6 Plus leads
MMAnswerBenchSource 78.9%83.8%Qwen3.6 Plus leads
AIME26Source 92.7%95.3%Qwen3.6 Plus leads
FrontierMath v2 (Tiers 1-3)Source 26.207%Not comparable
FrontierMath v2 (Tier 4)Source 8.333%Not comparable
Multilingual
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 57.9%Not comparable
MultimodalQwen3.6 Plus wins
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
MMMUSource 81.7%86.0%Qwen3.6 Plus leads
MMMU-ProSource 75.3%78.8%Qwen3.6 Plus leads
RealWorldQASource 85.3%Not comparable
OmniDocBench 1.5Source 89.9%Not comparable
CharXivSource 78%81.5%Qwen3.6 Plus leads
SimpleVQASource 58.9%Not comparable
CC-OCRSource 81.9%Not comparable
AI2D_TESTSource 92.7%Not comparable
RefCOCO (avg)Source 92.0%Not comparable
ODINW13Source 50.8%Not comparable
Video-MME (with subtitle)Source 86.6%Not comparable
Video-MME (w/o subtitle)Source 82.5%Not comparable
VideoMMMUSource 83.7%84.0%Qwen3.6 Plus leads
MLVU (M-Avg)Source 86.2%Not comparable
AA-MMMU-ProSource 75.0%78.0%Qwen3.6 Plus leads
MathVisionSource 88.0%Not comparable
ScreenSpot ProSource 68.2%Not comparable
V*Source 96.9%Not comparable
Design Arena WebsiteSource 1254Not comparable
Inst. Following
BenchmarkQwen3.6-35B-A3BQwen3.6 PlusResult
AA-IFBenchSource 64.4%75.2%Qwen3.6 Plus leads
IFEvalSource 94.3%Not comparable
IFBenchSource 75.8%Not comparable
Frequently Asked Questions (6)

Which is better, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus is ahead on BenchLM's provisional leaderboard, 63 to 59. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 51.5% and 61.6%.

Which is better for knowledge tasks, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for knowledge tasks in this comparison, averaging 57.5 versus 51.8. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 70.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6-35B-A3B has the edge for math in this comparison, averaging 88.2 versus 60.5. Inside this category, HMMT Feb 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for agentic tasks in this comparison, averaging 61.6 versus 51.5. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 79.8 versus 76.3. Inside this category, MMMU is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.