Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.5-35B-A3B vs Qwen3.6-35B-A3B

Data verified

Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.87/100
Margin
5.5pts
← winning
51.36/100
1 category wins2 category wins

Verified leaderboard positions: Qwen3.5-35B-A3B #30; Qwen3.6-35B-A3B #31

BenchAlign evidence: Qwen3.5-35B-A3B supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5-35B-A3B and Qwen3.6-35B-A3B share 20 comparable benchmark results. 3 of 8 categories are comparable. 9 results are unique to Qwen3.5-35B-A3B; 38 to Qwen3.6-35B-A3B.

Updated July 15, 2026
Shared results
20
Qwen3.5-35B-A3B only
9
Qwen3.6-35B-A3B only
38
Comparable categories
3 / 8

Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if knowledge is the priority.

Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 6 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.6-35B-A3B is clearly ahead on the provisional aggregate, 59 to 54. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.6-35B-A3B's sharpest advantage is in coding, where it averages 73.8 against 60.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 40.5% to 51.5%. Qwen3.5-35B-A3B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

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 Qwen3.5-35B-A3B and Qwen3.6-35B-A3B
CategoryQwen3.5-35B-A3BΔQwen3.6-35B-A3B
KnowledgeQwen3.5-35B-A3B81.7Margin← 29.9Qwen3.6-35B-A3B51.8
CodingQwen3.5-35B-A3B60.6Margin→ 13.2Qwen3.6-35B-A3B73.8
AgenticQwen3.5-35B-A3B51.0Margin→ 0.5Qwen3.6-35B-A3B51.5
ReasoningQwen3.5-35B-A3B59.0MarginNo overlapQwen3.6-35B-A3BNot measured
MathQwen3.5-35B-A3BNot measuredMarginNo overlapQwen3.6-35B-A3B88.2
MultilingualQwen3.5-35B-A3B81.0MarginNo overlapQwen3.6-35B-A3BNot measured
MultimodalQwen3.5-35B-A3BNot measuredMarginNo overlapQwen3.6-35B-A3B76.3
Inst. FollowingQwen3.5-35B-A3B91.9MarginNo overlapQwen3.6-35B-A3BNot measured

Decisive benchmark drivers

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

More
A · Qwen3.5-35B-A3BB · Qwen3.6-35B-A3B

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 40.5%B 51.5%
    Winner: Qwen3.6-35B-A3BΔ 11
    Terminal-Bench 2.0: Qwen3.5-35B-A3B scored 40.5%; Qwen3.6-35B-A3B scored 51.5%. Qwen3.6-35B-A3B wins this benchmark.

  2. SWE-bench Verified

    Coding
    Source ↗
    A 69.2%B 73.4%
    Winner: Qwen3.6-35B-A3BΔ 4.2
    SWE-bench Verified: Qwen3.5-35B-A3B scored 69.2%; Qwen3.6-35B-A3B scored 73.4%. Qwen3.6-35B-A3B wins this benchmark.

  3. GPQA

    Knowledge
    Source ↗
    A 84.2%B 86%
    Winner: Qwen3.6-35B-A3BΔ 1.8
    GPQA: Qwen3.5-35B-A3B scored 84.2%; Qwen3.6-35B-A3B scored 86%. Qwen3.6-35B-A3B wins this benchmark.

  4. SuperGPQA

    Knowledge
    Source ↗
    A 63.4%B 64.7%
    Winner: Qwen3.6-35B-A3BΔ 1.3
    SuperGPQA: Qwen3.5-35B-A3B scored 63.4%; Qwen3.6-35B-A3B scored 64.7%. Qwen3.6-35B-A3B wins this benchmark.

  5. MMLU-Pro

    Knowledge
    Source ↗
    A 85.3%B 85.2%
    Winner: Qwen3.5-35B-A3BΔ 0.1
    MMLU-Pro: Qwen3.5-35B-A3B scored 85.3%; Qwen3.6-35B-A3B scored 85.2%. Qwen3.5-35B-A3B wins this benchmark.

Operational comparison

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

MetricQwen3.5-35B-A3BQwen3.6-35B-A3BComparison
Input / output priceUSD per 1M tokensQwen3.5-35B-A3B$0 input / $0 outputQwen3.6-35B-A3BNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.5-35B-A3BNot availableQwen3.6-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5-35B-A3BNot availableQwen3.6-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5-35B-A3B262KQwen3.6-35B-A3B262KListed context windows are equal.

Benchmark Deep Dive

AgenticQwen3.6-35B-A3B wins
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
Terminal-Bench 2.0Source 40.5%51.5%Qwen3.6-35B-A3B leads
BrowseCompSource 61%—Not comparable
OSWorld-VerifiedSource 54.5%—Not comparable
τ²-bench resultsSource 89.2%95.3%Qwen3.6-35B-A3B leads
Gert LabsSource 28.96%42.65%Qwen3.6-35B-A3B leads
Claw-EvalSource —68.7%Not comparable
QwenClawBenchSource —52.6%Not comparable
QwenWebBenchSource —1397Not comparable
τ³-bench resultsSource —67.2%Not comparable
VITA-BenchSource —35.6%Not comparable
DeepPlanningSource —25.9%Not comparable
ToolathlonSource —26.9%Not comparable
MCP AtlasSource —62.8%Not comparable
WideResearchSource —60.1%Not comparable
AA Agentic IndexSource —21.4%Not comparable
GDPval-AASource —27.4%Not comparable
GDPval-AASource —1049Not comparable
CodingQwen3.6-35B-A3B wins
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
SWE-bench VerifiedSource 69.2%73.4%Qwen3.6-35B-A3B leads
SWE-RebenchSource 53.7%—Not comparable
Terminal-Bench HardSource 26.5%34.8%Qwen3.6-35B-A3B leads
AA-SciCodeSource 37.7%35.8%Qwen3.5-35B-A3B leads
SWE MultilingualSource —67.2%Not comparable
SWE-bench ProSource —49.5%Not comparable
Terminal-Bench 2.0Source —51.5%Not comparable
LiveCodeBenchSource —80.4%Not comparable
NL2RepoSource —29.4%Not comparable
AA Coding IndexSource —41.9%Not comparable
Reasoning
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
LongBench v2Source 59%—Not comparable
AA-LCRSource 62.7%63.7%Qwen3.6-35B-A3B leads
CritPtSource 0.9%0.3%Qwen3.5-35B-A3B leads
KnowledgeQwen3.5-35B-A3B wins
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
MMLU-ProSource 85.3%85.2%Qwen3.5-35B-A3B leads
SuperGPQASource 63.4%64.7%Qwen3.6-35B-A3B leads
GPQASource 84.2%86%Qwen3.6-35B-A3B leads
Artificial Analysis Intelligence IndexSource 29.3%31.6%Qwen3.6-35B-A3B leads
AA-GPQA DiamondSource 84.5%84.1%Qwen3.5-35B-A3B leads
AA-HLESource 19.7%20.2%Qwen3.6-35B-A3B leads
AA-Omniscience IndexSource -46.4%-21.4%Qwen3.6-35B-A3B leads
AA-Omniscience AccuracySource 20.5%18.9%Qwen3.5-35B-A3B leads
AA-Omniscience Hallucination RateSource 84.0%49.7%Qwen3.6-35B-A3B leads
C-EvalSource —90%Not comparable
HLESource —21.4%Not comparable
Math
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
HMMT Feb 2025Source —90.7%Not comparable
HMMT Nov 2025Source —89.1%Not comparable
HMMT Feb 2026Source —83.6%Not comparable
MMAnswerBenchSource —78.9%Not comparable
AIME26Source —92.7%Not comparable
Multilingual
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
MMLU-ProXSource 81%—Not comparable
Multimodal
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
MMMUSource 81.4%81.7%Qwen3.6-35B-A3B leads
MMVUSource 72.3%—Not comparable
MathVisionSource 83.9%—Not comparable
V*Source 92.7%—Not comparable
AA-MMMU-ProSource 72.7%75.0%Qwen3.6-35B-A3B leads
MMMU-ProSource —75.3%Not comparable
RealWorldQASource —85.3%Not comparable
OmniDocBench 1.5Source —89.9%Not comparable
CharXivSource —78%Not comparable
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%Not comparable
MLVU (M-Avg)Source —86.2%Not comparable
Inst. Following
BenchmarkQwen3.5-35B-A3BQwen3.6-35B-A3BResult
IFEvalSource 91.9%—Not comparable
AA-IFBenchSource 72.5%64.4%Qwen3.5-35B-A3B leads
Frequently Asked Questions (4)

Which is better, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B is ahead on BenchLM's provisional leaderboard, 59 to 54. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 40.5% and 51.5%.

Which is better for knowledge tasks, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 51.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 60.6. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has the edge for agentic tasks in this comparison, averaging 51.5 versus 51. Inside this category, Gert Labs 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 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.