Skip to main content

Model comparison

MiniMax M2.7 vs Qwen3.6-35B-A3B

Data verified

Head-to-head evidence from 23 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.03/100
Margin
12.7pts
← winning
51.36/100
1 category wins1 category wins

Verified leaderboard positions: MiniMax M2.7 unranked; Qwen3.6-35B-A3B #31

BenchAlign evidence: MiniMax M2.7 supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M2.7 and Qwen3.6-35B-A3B share 23 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to MiniMax M2.7; 35 to Qwen3.6-35B-A3B.

Updated July 15, 2026
Shared results
23
MiniMax M2.7 only
14
Qwen3.6-35B-A3B only
35
Comparable categories
2 / 8

Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if agentic is the priority or 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 5 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

Qwen3.6-35B-A3B is clearly ahead on the provisional aggregate, 59 to 52. 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 53.3. The single biggest benchmark swing on the page is SWE-bench Pro, 56.2% to 49.5%. MiniMax M2.7 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Qwen3.6-35B-A3B 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. Qwen3.6-35B-A3B gives you the larger context window at 262K, 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 Qwen3.6-35B-A3B
CategoryMiniMax M2.7ΔQwen3.6-35B-A3B
CodingMiniMax M2.753.3Margin 20.5Qwen3.6-35B-A3B73.8
AgenticMiniMax M2.757.0Margin 5.5Qwen3.6-35B-A3B51.5
KnowledgeMiniMax M2.7Not measuredMarginNo overlapQwen3.6-35B-A3B51.8
MathMiniMax M2.7Not measuredMarginNo overlapQwen3.6-35B-A3B88.2
MultimodalMiniMax M2.7Not measuredMarginNo overlapQwen3.6-35B-A3B76.3

Decisive benchmark drivers

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

More
A · MiniMax M2.7B · Qwen3.6-35B-A3B
  1. SWE-bench Pro

    Coding
    Source ↗
    A 56.2%B 49.5%
    Winner: MiniMax M2.7Δ 6.7
    SWE-bench Pro: MiniMax M2.7 scored 56.2%; Qwen3.6-35B-A3B scored 49.5%. MiniMax M2.7 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 57%B 51.5%
    Winner: MiniMax M2.7Δ 5.5
    Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Qwen3.6-35B-A3B scored 51.5%. MiniMax M2.7 wins this benchmark.

Operational comparison

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

MetricMiniMax M2.7Qwen3.6-35B-A3BComparison
Input / output priceUSD per 1M tokensMiniMax M2.7$0.3 input / $1.2 outputQwen3.6-35B-A3BNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniMax M2.745 tok/sQwen3.6-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M2.72.53 sQwen3.6-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M2.7200KQwen3.6-35B-A3B262KQwen3.6-35B-A3B lists the larger context window.

Benchmark Deep Dive

AgenticMiniMax M2.7 wins
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
Terminal-Bench 2.0Source 57%51.5%MiniMax M2.7 leads
τ²-bench resultsSource 84.8%95.3%Qwen3.6-35B-A3B leads
ToolathlonSource 46.3%26.9%MiniMax M2.7 leads
MLE-Bench LiteSource 66.6%Not comparable
MM-ClawBenchSource 62.7%Not comparable
Claw-EvalSource 48.7%68.7%Qwen3.6-35B-A3B leads
AA Agentic IndexSource 25.6%21.4%MiniMax M2.7 leads
APEX-Agents-AASource 10.6%Not comparable
GDPval-AASource 32.9%27.4%MiniMax M2.7 leads
GDPval-AASource 11581049MiniMax M2.7 leads
Gert LabsSource 40.40%42.65%Qwen3.6-35B-A3B leads
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
MCP AtlasSource 62.8%Not comparable
WideResearchSource 60.1%Not comparable
CodingQwen3.6-35B-A3B wins
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
SWE-bench Verified*Source 75.4%Not comparable
SWE-bench ProSource 56.2%49.5%MiniMax M2.7 leads
SWE-RebenchSource 51.9%Not comparable
SWE MultilingualSource 76.5%67.2%MiniMax M2.7 leads
Multi-SWE BenchSource 52.7%Not comparable
VIBE-ProSource 55.6%Not comparable
NL2RepoSource 39.8%29.4%MiniMax M2.7 leads
Vibe Code BenchSource 27.04%Not comparable
React Native EvalsSource 71.4%Not comparable
AA Coding IndexSource 52.6%41.9%MiniMax M2.7 leads
Terminal-Bench HardSource 39.4%34.8%MiniMax M2.7 leads
AA-SciCodeSource 47.0%35.8%MiniMax M2.7 leads
SWE-bench VerifiedSource 73.4%Not comparable
Terminal-Bench 2.0Source 51.5%Not comparable
LiveCodeBenchSource 80.4%Not comparable
Reasoning
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
AA-LCRSource 68.7%63.7%MiniMax M2.7 leads
CritPtSource 0.6%0.3%MiniMax M2.7 leads
Knowledge
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
GPQA-DSource 87.0%Not comparable
MMLU-Pro (Arcee)Source 80.8%Not comparable
Artificial Analysis Intelligence IndexSource 38.1%31.6%MiniMax M2.7 leads
AA-GPQA DiamondSource 87.4%84.1%MiniMax M2.7 leads
AA-HLESource 28.1%20.2%MiniMax M2.7 leads
AA-Omniscience IndexSource 0.7%-21.4%MiniMax M2.7 leads
AA-Omniscience AccuracySource 26.1%18.9%MiniMax M2.7 leads
AA-Omniscience Hallucination RateSource 34.4%49.7%MiniMax M2.7 leads
MMLU-ProSource 85.2%Not comparable
SuperGPQASource 64.7%Not comparable
C-EvalSource 90%Not comparable
GPQASource 86%Not comparable
HLESource 21.4%Not comparable
Math
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
AIME25 (Arcee)Source 80.0%Not comparable
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
Multimodal
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
GDPval-AASource 1495Not comparable
Design Arena WebsiteSource 1279Not comparable
MMMUSource 81.7%Not comparable
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
AA-MMMU-ProSource 75.0%Not comparable
Inst. Following
BenchmarkMiniMax M2.7Qwen3.6-35B-A3BResult
AA-IFBenchSource 75.7%64.4%MiniMax M2.7 leads
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B is ahead on BenchLM's provisional leaderboard, 59 to 52. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 56.2% and 49.5%.

Which is better for coding, MiniMax M2.7 or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 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 Qwen3.6-35B-A3B?

MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 versus 51.5. Inside this category, GDPval-AA 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.