Skip to main content

Model comparison

MiniMax M2.7 vs Qwen3.6 Plus

Data verified

Head-to-head evidence from 23 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.11/100
Margin
1.1pts
winning →
65.2/100
0 category wins2 category wins

Public leaderboard positions: MiniMax M2.7 #36 (Supported); Qwen3.6 Plus #30 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M2.7 and Qwen3.6 Plus share 23 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to MiniMax M2.7; 37 to Qwen3.6 Plus.

Updated July 23, 2026
Shared results
23
MiniMax M2.7 only
12
Qwen3.6 Plus only
37
Comparable categories
2 / 8

Pick Qwen3.6 Plus if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 6 evidence categories; 2 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 has the cleaner BenchAlign overall profile here, landing at 65.2 versus 64.11. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Qwen3.6 Plus's sharpest advantage is in coding, where it averages 70.3 against 53.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 57% to 61.6%.

Qwen3.6 Plus is the reasoning model in the pair, while MiniMax M2.7 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. Qwen3.6 Plus gives you the larger context window at 1M, compared with 200K for MiniMax M2.7.

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 M2.7 and Qwen3.6 Plus
CategoryMiniMax M2.7ΔQwen3.6 Plus
CodingMiniMax M2.753.3Margin 17.0Qwen3.6 Plus70.3
AgenticMiniMax M2.757.0Margin 4.6Qwen3.6 Plus61.6
ReasoningMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus62.0
KnowledgeMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus57.1
MathMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus60.5
MultilingualMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus84.7
MultimodalMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus79.8
Inst. FollowingMiniMax M2.7Not measuredMarginNo overlapQwen3.6 Plus82.3

Decisive benchmark drivers

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

More
A · MiniMax M2.7B · Qwen3.6 Plus
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 57%B 61.6%
    Winner: Qwen3.6 PlusΔ 4.6
    Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Qwen3.6 Plus scored 61.6%. Qwen3.6 Plus wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 56.2%B 56.6%
    Winner: Qwen3.6 PlusΔ 0.4
    SWE-bench Pro: MiniMax M2.7 scored 56.2%; Qwen3.6 Plus scored 56.6%. Qwen3.6 Plus wins this benchmark.

Operational comparison

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

MetricMiniMax M2.7Qwen3.6 PlusComparison
Input / output priceUSD per 1M tokensMiniMax M2.7$0.3 input / $1.2 outputQwen3.6 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniMax M2.745 tok/sQwen3.6 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M2.72.53 sQwen3.6 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M2.7200KQwen3.6 Plus1MQwen3.6 Plus lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.6 Plus wins
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
Terminal-Bench 2.0Source 57%61.6%Qwen3.6 Plus leads
τ²-bench resultsSource 84.8%97.7%Qwen3.6 Plus leads
ToolathlonSource 46.3%39.8%MiniMax M2.7 leads
MLE-Bench LiteSource 66.6%Not comparable
MM-ClawBenchSource 62.7%Not comparable
Claw-EvalSource 48.7%58.8%Qwen3.6 Plus leads
AA Agentic IndexSource 25.6%27.6%Qwen3.6 Plus leads
APEX-Agents-AASource 10.6%Not comparable
GDPval-AASource 32.9%31.8%MiniMax M2.7 leads
GDPval-AASource 11581135MiniMax M2.7 leads
Gert LabsSource 40.40%50.60%Qwen3.6 Plus leads
QwenClawBenchSource 57.2%Not comparable
τ³-bench resultsSource 70.7%Not comparable
VITA-BenchSource 44.3%Not comparable
DeepPlanningSource 41.5%Not comparable
MCP AtlasSource 48.2%Not comparable
MCP-TasksSource 74.1%Not comparable
WideResearchSource 74.3%Not comparable
ResearchClawBenchSource 18.0%Not comparable
CodingQwen3.6 Plus wins
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
SWE-bench Verified*Source 75.4%Not comparable
SWE-bench ProSource 56.2%56.6%Qwen3.6 Plus leads
SWE-RebenchSource 51.9%Not comparable
SWE MultilingualSource 76.5%73.8%MiniMax M2.7 leads
Multi-SWE BenchSource 52.7%Not comparable
VIBE-ProSource 55.6%Not comparable
NL2RepoSource 39.8%Not comparable
Vibe Code BenchSource 27.04%25.56%MiniMax M2.7 leads
React Native EvalsSource 71.4%Not comparable
AA Coding IndexSource 52.6%54.5%Qwen3.6 Plus leads
AA-SciCodeSource 47.0%40.7%MiniMax M2.7 leads
SWE-bench VerifiedSource 78.8%Not comparable
LiveCodeBench v6Source 87.1%Not comparable
Reasoning
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
AA-LCRSource 68.7%69.7%Qwen3.6 Plus leads
CritPtSource 0.6%2.9%Qwen3.6 Plus leads
AI-NeedleSource 68.3%Not comparable
LongBench v2Source 62%Not comparable
Knowledge
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
GPQA-DSource 87.0%Not comparable
MMLU-Pro (Arcee)Source 80.8%Not comparable
Artificial Analysis Intelligence IndexSource 38.1%39.6%Qwen3.6 Plus leads
AA-GPQA DiamondSource 87.4%88.2%Qwen3.6 Plus leads
AA-HLESource 28.1%25.7%MiniMax M2.7 leads
AA-Omniscience IndexSource 0.7%2.7%Qwen3.6 Plus leads
AA-Omniscience AccuracySource 26.1%26.2%Qwen3.6 Plus leads
AA-Omniscience Hallucination RateSource 34.4%32.0%Qwen3.6 Plus leads
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
Math
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
AIME25 (Arcee)Source 80.0%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 M2.7Qwen3.6 PlusResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 57.9%Not comparable
Multimodal
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
Design Arena WebsiteSource 12751249MiniMax M2.7 leads
MMMUSource 86.0%Not comparable
MMMU-ProSource 78.8%Not comparable
MathVisionSource 88.0%Not comparable
VideoMMMUSource 84.0%Not comparable
ScreenSpot ProSource 68.2%Not comparable
CharXivSource 81.5%Not comparable
V*Source 96.9%Not comparable
AA-MMMU-ProSource 78.0%Not comparable
Inst. Following
BenchmarkMiniMax M2.7Qwen3.6 PlusResult
AA-IFBenchSource 75.7%75.2%MiniMax M2.7 leads
IFEvalSource 94.3%Not comparable
IFBenchSource 75.8%Not comparable
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus is ahead on BenchLM's BenchAlign leaderboard, 65.2 to 64.11. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 57% and 61.6%.

Which is better for coding, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for coding in this comparison, averaging 70.3 versus 53.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus has the edge for agentic tasks in this comparison, averaging 61.6 versus 57. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

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.