Skip to main content
BenchLM
Advertise

Model comparison

MiniMax M2.7 vs Qwen3.7 Max

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
8.7pts
winning →
72.84/100
0 category wins2 category wins

Public leaderboard positions: MiniMax M2.7 #36 (Supported); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M2.7 and Qwen3.7 Max share 23 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to MiniMax M2.7; 35 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
23
MiniMax M2.7 only
12
Qwen3.7 Max only
35
Comparable categories
2 / 8

Pick Qwen3.7 Max 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

Qwen3.7 Max is clearly ahead on the BenchAlign aggregate, 72.84 to 64.11. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.7 Max's sharpest advantage is in coding, where it averages 77.9 against 53.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 57% to 69.7%.

Qwen3.7 Max 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. Qwen3.7 Max 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 Qwen3.7 Max
CategoryMiniMax M2.7ΔQwen3.7 Max
CodingMiniMax M2.753.3Margin→ 24.6Qwen3.7 Max77.9
AgenticMiniMax M2.757.0Margin→ 12.7Qwen3.7 Max69.7
ReasoningMiniMax M2.7Not measuredMarginNo overlapQwen3.7 Max90.4
KnowledgeMiniMax M2.7Not measuredMarginNo overlapQwen3.7 Max64.2
MathMiniMax M2.7Not measuredMarginNo overlapQwen3.7 Max97.1
MultilingualMiniMax M2.7Not measuredMarginNo overlapQwen3.7 Max87.0
Inst. FollowingMiniMax M2.7Not measuredMarginNo overlapQwen3.7 Max84.4

Decisive benchmark drivers

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

More
A · MiniMax M2.7B · Qwen3.7 Max

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 57%B 69.7%
    Winner: Qwen3.7 MaxΔ 12.7
    Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Qwen3.7 Max scored 69.7%. Qwen3.7 Max wins this benchmark.

  2. SWE-bench Pro

    Coding
    Source ↗
    A 56.2%B 60.6%
    Winner: Qwen3.7 MaxΔ 4.4
    SWE-bench Pro: MiniMax M2.7 scored 56.2%; Qwen3.7 Max scored 60.6%. Qwen3.7 Max wins this benchmark.

Operational comparison

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

MetricMiniMax M2.7Qwen3.7 MaxComparison
Input / output priceUSD per 1M tokensMiniMax M2.7$0.3 input / $1.2 outputQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniMax M2.745 tok/sQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M2.72.53 sQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M2.7200KQwen3.7 Max1MQwen3.7 Max lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.7 Max wins
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
Terminal-Bench 2.0Source 57%69.7%Qwen3.7 Max leads
τ²-bench resultsSource 84.8%94.7%Qwen3.7 Max leads
ToolathlonSource 46.3%—Not comparable
MLE-Bench LiteSource 66.6%—Not comparable
MM-ClawBenchSource 62.7%—Not comparable
Claw-EvalSource 48.7%65.2%Qwen3.7 Max leads
AA Agentic IndexSource 25.6%30.6%Qwen3.7 Max leads
APEX-Agents-AASource 10.6%—Not comparable
GDPval-AASource 32.9%38.7%Qwen3.7 Max leads
GDPval-AASource 11581273Qwen3.7 Max leads
Gert LabsSource 40.40%64.27%Qwen3.7 Max leads
QwenClawBenchSource —64.3%Not comparable
QwenWebBenchSource —1568Not comparable
BFCL v4Source —75.0%Not comparable
MCP AtlasSource —76.4%Not comparable
VITA-BenchSource —47.9%Not comparable
HLE w/ toolsSource —53.5%Not comparable
ResearchClawBenchSource —18.7%Not comparable
AA BriefcaseSource —908Not comparable
AA AutomationBenchSource —25.6%Not comparable
AA EnterpriseOps-GymSource —45.0%Not comparable
AA ITBenchSource —42.5%Not comparable
terminalBenchHardSource —50.8%Not comparable
aaTerminalBench21Source —74.5%Not comparable
AA Harvey LABSource —83.4%Not comparable
CodingQwen3.7 Max wins
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
SWE-bench Verified*Source 75.4%—Not comparable
SWE-bench ProSource 56.2%60.6%Qwen3.7 Max leads
SWE-RebenchSource 51.9%—Not comparable
SWE MultilingualSource 76.5%78.3%Qwen3.7 Max leads
Multi-SWE BenchSource 52.7%—Not comparable
VIBE-ProSource 55.6%—Not comparable
NL2RepoSource 39.8%47.2%Qwen3.7 Max leads
Vibe Code BenchSource 27.04%—Not comparable
React Native EvalsSource 71.4%—Not comparable
AA Coding IndexSource 52.6%66.0%Qwen3.7 Max leads
AA-SciCodeSource 47.0%48.8%Qwen3.7 Max leads
SWE-bench VerifiedSource —80.4%Not comparable
SciCodeSource —53.5%Not comparable
LiveCodeBenchSource —91.6%Not comparable
Terminal-Bench 2.0Source —69.7%Not comparable
Reasoning
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
AA-LCRSource 68.7%69.0%Qwen3.7 Max leads
CritPtSource 0.6%13.4%Qwen3.7 Max leads
MRCRv2Source —90.4%Not comparable
Knowledge
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
GPQA-DSource 87.0%92.4%Qwen3.7 Max leads
MMLU-Pro (Arcee)Source 80.8%—Not comparable
Artificial Analysis Intelligence IndexSource 38.1%46.0%Qwen3.7 Max leads
AA-GPQA DiamondSource 87.4%92.3%Qwen3.7 Max leads
AA-HLESource 28.1%38.1%Qwen3.7 Max leads
AA-Omniscience IndexSource 0.7%14.1%Qwen3.7 Max leads
AA-Omniscience AccuracySource 26.1%30.1%Qwen3.7 Max leads
AA-Omniscience Hallucination RateSource 34.4%22.9%Qwen3.7 Max leads
GPQASource —92.4%Not comparable
HLESource —41.4%Not comparable
MMLU-ProSource —89.6%Not comparable
MMLU-ReduxSource —95%Not comparable
SuperGPQASource —73.6%Not comparable
MMMLUSource —90.3%Not comparable
Math
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
AIME25 (Arcee)Source 80.0%—Not comparable
HMMT Feb 2026Source —97.1%Not comparable
IMOAnswerBenchSource —90.0%Not comparable
ApexSource —44.5%Not comparable
Multilingual
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
MMLU-ProXSource —87%Not comparable
NOVA-63Source —59.0%Not comparable
INCLUDESource —86.2%Not comparable
MAXIFESource —89.2%Not comparable
PolyMathSource —86.5%Not comparable
Multimodal
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
Design Arena WebsiteSource 12751293Qwen3.7 Max leads
Inst. Following
BenchmarkMiniMax M2.7Qwen3.7 MaxResult
AA-IFBenchSource 75.7%80.5%Qwen3.7 Max leads
IFEvalSource —94.3%Not comparable
IFBenchSource —79.1%Not comparable
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Qwen3.7 Max?

Qwen3.7 Max is ahead on BenchLM's BenchAlign leaderboard, 72.84 to 64.11. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 57% and 69.7%.

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

Qwen3.7 Max has the edge for coding in this comparison, averaging 77.9 versus 53.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

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

Qwen3.7 Max has the edge for agentic tasks in this comparison, averaging 69.7 versus 57. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

MiniMax Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.