Skip to main content

Model comparison

Gemma 4 31B vs Qwen3.6-35B-A3B

Data verified

Head-to-head evidence from 22 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

61/100
Margin
9.6pts
← winning
51.36/100
2 category wins1 category wins

Verified leaderboard positions: Gemma 4 31B unranked; Qwen3.6-35B-A3B #31

BenchAlign evidence: Gemma 4 31B supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and Qwen3.6-35B-A3B share 22 comparable benchmark results. 3 of 8 categories are comparable. 8 results are unique to Gemma 4 31B; 36 to Qwen3.6-35B-A3B.

Updated July 15, 2026
Shared results
22
Gemma 4 31B only
8
Qwen3.6-35B-A3B only
36
Comparable categories
3 / 8

Pick Gemma 4 31B if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if coding is the priority or you need the larger 262K context window.

Confidence note. This is a partial-evidence comparison with 22 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

Gemma 4 31B has the cleaner provisional overall profile here, landing at 62 versus 59. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemma 4 31B's sharpest advantage is in knowledge, where it averages 53.3 against 51.8. The single biggest benchmark swing on the page is HLE, 26.5% to 21.4%. Qwen3.6-35B-A3B does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 256K for Gemma 4 31B.

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 Gemma 4 31B and Qwen3.6-35B-A3B
CategoryGemma 4 31BΔQwen3.6-35B-A3B
CodingGemma 4 31B41.6Margin 32.2Qwen3.6-35B-A3B73.8
KnowledgeGemma 4 31B53.3Margin 1.5Qwen3.6-35B-A3B51.8
MultimodalGemma 4 31B76.9Margin 0.6Qwen3.6-35B-A3B76.3
AgenticGemma 4 31BNot measuredMarginNo overlapQwen3.6-35B-A3B51.5
MathGemma 4 31BNot measuredMarginNo overlapQwen3.6-35B-A3B88.2

Decisive benchmark drivers

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

More
A · Gemma 4 31BB · Qwen3.6-35B-A3B
  1. HLE

    Knowledge
    Source ↗
    A 26.5%B 21.4%
    Winner: Gemma 4 31BΔ 5.1
    HLE: Gemma 4 31B scored 26.5%; Qwen3.6-35B-A3B scored 21.4%. Gemma 4 31B wins this benchmark.
  2. GPQA

    Knowledge
    Source ↗
    A 84.3%B 86%
    Winner: Qwen3.6-35B-A3BΔ 1.7
    GPQA: Gemma 4 31B scored 84.3%; Qwen3.6-35B-A3B scored 86%. Qwen3.6-35B-A3B wins this benchmark.
  3. MMMU-Pro

    Multimodal
    Source ↗
    A 76.9%B 75.3%
    Winner: Gemma 4 31BΔ 1.6
    MMMU-Pro: Gemma 4 31B scored 76.9%; Qwen3.6-35B-A3B scored 75.3%. Gemma 4 31B wins this benchmark.

Operational comparison

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

MetricGemma 4 31BQwen3.6-35B-A3BComparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputQwen3.6-35B-A3BNot availableA complete price comparison is not available.
Generation speedtokens per secondGemma 4 31BNot availableQwen3.6-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableQwen3.6-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KQwen3.6-35B-A3B262KQwen3.6-35B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
AA Agentic IndexSource 14.4%21.4%Qwen3.6-35B-A3B leads
τ²-bench resultsSource 59.9%95.3%Qwen3.6-35B-A3B leads
GDPval-AASource 15.2%27.4%Qwen3.6-35B-A3B leads
GDPval-AASource 8041049Qwen3.6-35B-A3B leads
Gert LabsSource 35.26%42.65%Qwen3.6-35B-A3B leads
AA EnterpriseOps-GymSource 28.3%Not comparable
AA Harvey LABSource 0.0%Not comparable
AA ITBenchSource 37.3%Not comparable
AA Tau3 BankingSource 15.1%Not comparable
Terminal-Bench 2.0Source 51.5%Not comparable
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
CodingQwen3.6-35B-A3B wins
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%41.9%Gemma 4 31B leads
Terminal-Bench HardSource 36.4%34.8%Gemma 4 31B leads
AA-SciCodeSource 43.4%35.8%Gemma 4 31B leads
SWE-bench VerifiedSource 73.4%Not comparable
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
Reasoning
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
AA-LCRSource 62.0%63.7%Qwen3.6-35B-A3B leads
CritPtSource 1.4%0.3%Gemma 4 31B leads
KnowledgeGemma 4 31B wins
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
GPQASource 84.3%86%Qwen3.6-35B-A3B leads
MMLU-ProSource 85.2%85.2%Tie
HLESource 26.5%21.4%Gemma 4 31B leads
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%31.6%Qwen3.6-35B-A3B leads
AA-GPQA DiamondSource 85.7%84.1%Gemma 4 31B leads
AA-HLESource 22.7%20.2%Gemma 4 31B leads
AA-Omniscience IndexSource -45.4%-21.4%Qwen3.6-35B-A3B leads
AA-Omniscience AccuracySource 19.9%18.9%Gemma 4 31B leads
AA-Omniscience Hallucination RateSource 81.6%49.7%Qwen3.6-35B-A3B leads
AA Openness IndexSource 38.9%Not comparable
SuperGPQASource 64.7%Not comparable
C-EvalSource 90%Not comparable
Math
BenchmarkGemma 4 31BQwen3.6-35B-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
MultimodalGemma 4 31B wins
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
MMMU-ProSource 76.9%75.3%Gemma 4 31B leads
AA-MMMU-ProSource 73.4%75.0%Qwen3.6-35B-A3B leads
MMMUSource 81.7%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
BenchmarkGemma 4 31BQwen3.6-35B-A3BResult
AA-IFBenchSource 75.6%64.4%Gemma 4 31B leads
Frequently Asked Questions (4)

Which is better, Gemma 4 31B or Qwen3.6-35B-A3B?

Gemma 4 31B is ahead on BenchLM's provisional leaderboard, 62 to 59. The biggest single separator in this matchup is HLE, where the scores are 26.5% and 21.4%.

Which is better for knowledge tasks, Gemma 4 31B or Qwen3.6-35B-A3B?

Gemma 4 31B has the edge for knowledge tasks in this comparison, averaging 53.3 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, Gemma 4 31B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 41.6. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Gemma 4 31B or Qwen3.6-35B-A3B?

Gemma 4 31B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 76.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Gemma 4 31B
API / mo$0
Self-host / mo$429
Break-even
Qwen3.6-35B-A3B
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

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.