Skip to main content

Model comparison

MiniMax M3 vs Qwen3.6 Plus

Data verified

Head-to-head evidence from 26 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

MiniMax
69.8/100
Margin
4.8pts
← winning
65.05/100
3 category wins1 category wins

Verified leaderboard positions: MiniMax M3 #18; Qwen3.6 Plus #14

BenchAlign evidence: MiniMax M3 supported; Qwen3.6 Plus supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M3 and Qwen3.6 Plus share 26 comparable benchmark results. 4 of 8 categories are comparable. 19 results are unique to MiniMax M3; 35 to Qwen3.6 Plus.

Updated July 16, 2026
Shared results
26
MiniMax M3 only
19
Qwen3.6 Plus only
35
Comparable categories
4 / 8

Pick MiniMax M3 if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if multimodal & grounded is the priority or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 26 shared benchmark results across 6 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

MiniMax M3 is clearly ahead on the provisional aggregate, 70 to 63. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

MiniMax M3's sharpest advantage is in mathematics, where it averages 85.7 against 60.5. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 66% to 61.6%. Qwen3.6 Plus does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

Qwen3.6 Plus is the reasoning model in the pair, while MiniMax M3 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.

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 MiniMax M3 and Qwen3.6 Plus
CategoryMiniMax M3ΔQwen3.6 Plus
MathMiniMax M385.7Margin 25.2Qwen3.6 Plus60.5
MultimodalMiniMax M364.9Margin 14.9Qwen3.6 Plus79.8
AgenticMiniMax M372.3Margin 10.7Qwen3.6 Plus61.6
CodingMiniMax M372.2Margin 1.9Qwen3.6 Plus70.3
ReasoningMiniMax M3Not measuredMarginNo overlapQwen3.6 Plus62.0
KnowledgeMiniMax M3Not measuredMarginNo overlapQwen3.6 Plus57.5
MultilingualMiniMax M3Not measuredMarginNo overlapQwen3.6 Plus84.7
Inst. FollowingMiniMax M3Not measuredMarginNo overlapQwen3.6 Plus82.3

Decisive benchmark drivers

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

More
A · MiniMax M3B · Qwen3.6 Plus
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 66%B 61.6%
    Winner: MiniMax M3Δ 4.4
    Terminal-Bench 2.0: MiniMax M3 scored 66%; Qwen3.6 Plus scored 61.6%. MiniMax M3 wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 59%B 56.6%
    Winner: MiniMax M3Δ 2.4
    SWE-bench Pro: MiniMax M3 scored 59%; Qwen3.6 Plus scored 56.6%. MiniMax M3 wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 80.5%B 78.8%
    Winner: MiniMax M3Δ 1.7
    SWE-bench Verified: MiniMax M3 scored 80.5%; Qwen3.6 Plus scored 78.8%. MiniMax M3 wins this benchmark.
  4. MMMU-Pro

    Multimodal
    Source ↗
    A 78.1%B 78.8%
    Winner: Qwen3.6 PlusΔ 0.7
    MMMU-Pro: MiniMax M3 scored 78.1%; 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.

MetricMiniMax M3Qwen3.6 PlusComparison
Input / output priceUSD per 1M tokensMiniMax M3$0.3 input / $1.2 outputQwen3.6 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniMax M3Not availableQwen3.6 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M3Not availableQwen3.6 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M31MQwen3.6 Plus1MListed context windows are equal.

Benchmark Deep Dive

AgenticMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.6 PlusResult
Terminal-Bench 2.0Source 66%61.6%MiniMax M3 leads
BrowseCompSource 83.5%Not comparable
OSWorld-VerifiedSource 70.1%Not comparable
MCP AtlasSource 74.2%48.2%MiniMax M3 leads
Claw-EvalSource 74.5%58.8%MiniMax M3 leads
AA Agentic IndexSource 35.4%27.6%MiniMax M3 leads
τ²-bench resultsSource 88.9%97.7%Qwen3.6 Plus leads
GDPval-AASource 44.7%31.8%MiniMax M3 leads
GDPval-AASource 13951135MiniMax M3 leads
GDPval rubricsSource 74.7%Not comparable
BankerToolBenchSource 76.1%Not comparable
ResearchClawBenchSource 19.8%18.0%MiniMax M3 leads
OSWorld 2.0Source 4.6%Not comparable
AA BriefcaseSource 1110Not comparable
AA EnterpriseOps-GymSource 32.1%Not comparable
AA Harvey LABSource 6.7%Not comparable
QwenClawBenchSource 57.2%Not comparable
τ³-bench resultsSource 70.7%Not comparable
VITA-BenchSource 44.3%Not comparable
DeepPlanningSource 41.5%Not comparable
ToolathlonSource 39.8%Not comparable
MCP-TasksSource 74.1%Not comparable
WideResearchSource 74.3%Not comparable
Gert LabsSource 50.60%Not comparable
CodingMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.6 PlusResult
SWE-bench VerifiedSource 80.5%78.8%MiniMax M3 leads
SWE-bench ProSource 59%56.6%MiniMax M3 leads
Terminal-Bench 2.0Source 66.0%Not comparable
NL2RepoSource 42.1%Not comparable
AA Coding IndexSource 58.6%54.5%MiniMax M3 leads
Terminal-Bench HardSource 42.4%43.9%Qwen3.6 Plus leads
AA-SciCodeSource 45.4%40.7%MiniMax M3 leads
VIBE V2Source 50.1%Not comparable
SVG-BenchSource 63.7%Not comparable
KernelBench HardSource 28.8%Not comparable
AA Terminal-Bench 2.1Source 65.2%Not comparable
SWE MultilingualSource 73.8%Not comparable
LiveCodeBench v6Source 87.1%Not comparable
Vibe Code BenchSource 25.56%Not comparable
Reasoning
BenchmarkMiniMax M3Qwen3.6 PlusResult
AA-LCRSource 74.0%69.7%MiniMax M3 leads
CritPtSource 3.7%2.9%MiniMax M3 leads
AI-NeedleSource 68.3%Not comparable
LongBench v2Source 62%Not comparable
Knowledge
BenchmarkMiniMax M3Qwen3.6 PlusResult
Artificial Analysis Intelligence IndexSource 44.4%39.6%MiniMax M3 leads
AA-GPQA DiamondSource 92.9%88.2%MiniMax M3 leads
AA-HLESource 37.1%25.7%MiniMax M3 leads
AA-Omniscience IndexSource 1.4%2.7%Qwen3.6 Plus leads
AA-Omniscience AccuracySource 15.0%26.2%Qwen3.6 Plus leads
AA-Omniscience Hallucination RateSource 16.1%32.0%MiniMax M3 leads
AA Openness IndexSource 33.3%Not comparable
GPQASource 90.4%Not comparable
SuperGPQASource 71.6%Not comparable
MMLU-ProSource 88.5%Not comparable
MMLU-ReduxSource 94.5%Not comparable
C-EvalSource 93.3%Not comparable
HLESource 28.8%Not comparable
MathMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.6 PlusResult
USAMO 2026Source 85.7%Not comparable
AIME26Source 95.3%Not comparable
HMMT Feb 2025Source 96.7%Not comparable
HMMT Nov 2025Source 94.6%Not comparable
HMMT Feb 2026Source 87.8%Not comparable
MMAnswerBenchSource 83.8%Not comparable
FrontierMath v2 (Tiers 1-3)Source 26.207%Not comparable
FrontierMath v2 (Tier 4)Source 8.333%Not comparable
Multilingual
BenchmarkMiniMax M3Qwen3.6 PlusResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 57.9%Not comparable
MultimodalQwen3.6 Plus wins
BenchmarkMiniMax M3Qwen3.6 PlusResult
OfficeQA ProSource 45.1%Not comparable
OmniDocBench 1.5Source 91.6%Not comparable
MMMU-ProSource 78.1%78.8%Qwen3.6 Plus leads
VideoMMMUSource 84.6%84.0%MiniMax M3 leads
Video-MME (with subtitle)Source 85.4%Not comparable
Design Arena WebsiteSource 12941254MiniMax M3 leads
AA-MMMU-ProSource 78.6%78.0%MiniMax M3 leads
MMMUSource 86.0%Not comparable
MathVisionSource 88.0%Not comparable
ScreenSpot ProSource 68.2%Not comparable
CharXivSource 81.5%Not comparable
V*Source 96.9%Not comparable
Inst. Following
BenchmarkMiniMax M3Qwen3.6 PlusResult
AA-IFBenchSource 82.9%75.2%MiniMax M3 leads
IFEvalSource 94.3%Not comparable
IFBenchSource 75.8%Not comparable
Frequently Asked Questions (5)

Which is better, MiniMax M3 or Qwen3.6 Plus?

MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 63. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 66% and 61.6%.

Which is better for coding, MiniMax M3 or Qwen3.6 Plus?

MiniMax M3 has the edge for coding in this comparison, averaging 72.2 versus 70.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for math, MiniMax M3 or Qwen3.6 Plus?

MiniMax M3 has the edge for math in this comparison, averaging 85.7 versus 60.5. Qwen3.6 Plus stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, MiniMax M3 or Qwen3.6 Plus?

MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 61.6. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, MiniMax M3 or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 79.8 versus 64.9. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 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.