Skip to main content

Model comparison

MiniMax M3 vs Qwen3.7 Max

Data verified

Head-to-head evidence from 28 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

MiniMax
69.8/100
Margin
8.8pts
← winning
60.99/100
1 category wins2 category wins

Verified leaderboard positions: MiniMax M3 #18; Qwen3.7 Max #2

BenchAlign evidence: MiniMax M3 supported; Qwen3.7 Max estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M3 and Qwen3.7 Max share 28 comparable benchmark results. 3 of 8 categories are comparable. 17 results are unique to MiniMax M3; 29 to Qwen3.7 Max.

Updated July 16, 2026
Shared results
28
MiniMax M3 only
17
Qwen3.7 Max only
29
Comparable categories
3 / 8

Pick Qwen3.7 Max if you want the stronger benchmark profile. MiniMax M3 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 28 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

Qwen3.7 Max is clearly ahead on the provisional aggregate, 83 to 70. 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 mathematics, where it averages 97.1 against 85.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 66% to 69.7%. MiniMax M3 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Qwen3.7 Max 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 Qwen3.7 Max
CategoryMiniMax M3ΔQwen3.7 Max
MathMiniMax M385.7Margin 11.4Qwen3.7 Max97.1
CodingMiniMax M372.2Margin 5.7Qwen3.7 Max77.9
AgenticMiniMax M372.3Margin 2.6Qwen3.7 Max69.7
ReasoningMiniMax M3Not measuredMarginNo overlapQwen3.7 Max90.4
KnowledgeMiniMax M3Not measuredMarginNo overlapQwen3.7 Max64.5
MultilingualMiniMax M3Not measuredMarginNo overlapQwen3.7 Max87.0
MultimodalMiniMax M364.9MarginNo overlapQwen3.7 MaxNot measured
Inst. FollowingMiniMax M3Not measuredMarginNo overlapQwen3.7 Max84.4

Decisive benchmark drivers

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

More
A · MiniMax M3B · Qwen3.7 Max
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 66%B 69.7%
    Winner: Qwen3.7 MaxΔ 3.7
    Terminal-Bench 2.0: MiniMax M3 scored 66%; Qwen3.7 Max scored 69.7%. Qwen3.7 Max wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 59%B 60.6%
    Winner: Qwen3.7 MaxΔ 1.6
    SWE-bench Pro: MiniMax M3 scored 59%; Qwen3.7 Max scored 60.6%. Qwen3.7 Max wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 80.5%B 80.4%
    Winner: MiniMax M3Δ 0.1
    SWE-bench Verified: MiniMax M3 scored 80.5%; Qwen3.7 Max scored 80.4%. MiniMax M3 wins this benchmark.

Operational comparison

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

MetricMiniMax M3Qwen3.7 MaxComparison
Input / output priceUSD per 1M tokensMiniMax M3$0.3 input / $1.2 outputQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniMax M3Not availableQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M3Not availableQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M31MQwen3.7 Max1MListed context windows are equal.

Benchmark Deep Dive

AgenticMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.7 MaxResult
Terminal-Bench 2.0Source 66%69.7%Qwen3.7 Max leads
BrowseCompSource 83.5%Not comparable
OSWorld-VerifiedSource 70.1%Not comparable
MCP AtlasSource 74.2%76.4%Qwen3.7 Max leads
Claw-EvalSource 74.5%65.2%MiniMax M3 leads
AA Agentic IndexSource 35.4%30.6%MiniMax M3 leads
τ²-bench resultsSource 88.9%94.7%Qwen3.7 Max leads
GDPval-AASource 44.7%38.7%MiniMax M3 leads
GDPval-AASource 13951273MiniMax M3 leads
GDPval rubricsSource 74.7%Not comparable
BankerToolBenchSource 76.1%Not comparable
ResearchClawBenchSource 19.8%18.7%MiniMax M3 leads
OSWorld 2.0Source 4.6%Not comparable
AA BriefcaseSource 1110908MiniMax M3 leads
AA EnterpriseOps-GymSource 32.1%45.0%Qwen3.7 Max leads
AA Harvey LABSource 6.7%Not comparable
QwenClawBenchSource 64.3%Not comparable
QwenWebBenchSource 1568Not comparable
BFCL v4Source 75.0%Not comparable
VITA-BenchSource 47.9%Not comparable
HLE w/ toolsSource 53.5%Not comparable
Gert LabsSource 64.27%Not comparable
AA AutomationBenchSource 25.6%Not comparable
AA ITBenchSource 42.5%Not comparable
CodingQwen3.7 Max wins
BenchmarkMiniMax M3Qwen3.7 MaxResult
SWE-bench VerifiedSource 80.5%80.4%MiniMax M3 leads
SWE-bench ProSource 59%60.6%Qwen3.7 Max leads
Terminal-Bench 2.0Source 66.0%69.7%Qwen3.7 Max leads
NL2RepoSource 42.1%47.2%Qwen3.7 Max leads
AA Coding IndexSource 58.6%66.0%Qwen3.7 Max leads
Terminal-Bench HardSource 42.4%50.8%Qwen3.7 Max leads
AA-SciCodeSource 45.4%48.8%Qwen3.7 Max 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%74.5%Qwen3.7 Max leads
SWE MultilingualSource 78.3%Not comparable
SciCodeSource 53.5%Not comparable
LiveCodeBenchSource 91.6%Not comparable
Reasoning
BenchmarkMiniMax M3Qwen3.7 MaxResult
AA-LCRSource 74.0%69.0%MiniMax M3 leads
CritPtSource 3.7%13.4%Qwen3.7 Max leads
MRCRv2Source 90.4%Not comparable
Knowledge
BenchmarkMiniMax M3Qwen3.7 MaxResult
Artificial Analysis Intelligence IndexSource 44.4%46.0%Qwen3.7 Max leads
AA-GPQA DiamondSource 92.9%92.3%MiniMax M3 leads
AA-HLESource 37.1%38.1%Qwen3.7 Max leads
AA-Omniscience IndexSource 1.4%14.1%Qwen3.7 Max leads
AA-Omniscience AccuracySource 15.0%30.1%Qwen3.7 Max leads
AA-Omniscience Hallucination RateSource 16.1%22.9%MiniMax M3 leads
AA Openness IndexSource 33.3%Not comparable
GPQASource 92.4%Not comparable
GPQA-DSource 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
MathQwen3.7 Max wins
BenchmarkMiniMax M3Qwen3.7 MaxResult
USAMO 2026Source 85.7%Not comparable
HMMT Feb 2026Source 97.1%Not comparable
IMOAnswerBenchSource 90.0%Not comparable
ApexSource 44.5%Not comparable
Multilingual
BenchmarkMiniMax M3Qwen3.7 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 M3Qwen3.7 MaxResult
OfficeQA ProSource 45.1%Not comparable
OmniDocBench 1.5Source 91.6%Not comparable
MMMU-ProSource 78.1%Not comparable
VideoMMMUSource 84.6%Not comparable
Video-MME (with subtitle)Source 85.4%Not comparable
Design Arena WebsiteSource 12941296Qwen3.7 Max leads
AA-MMMU-ProSource 78.6%Not comparable
Inst. Following
BenchmarkMiniMax M3Qwen3.7 MaxResult
AA-IFBenchSource 82.9%80.5%MiniMax M3 leads
IFEvalSource 94.3%Not comparable
IFBenchSource 79.1%Not comparable
Frequently Asked Questions (4)

Which is better, MiniMax M3 or Qwen3.7 Max?

Qwen3.7 Max is ahead on BenchLM's provisional leaderboard, 83 to 70. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 66% and 69.7%.

Which is better for coding, MiniMax M3 or Qwen3.7 Max?

Qwen3.7 Max has the edge for coding in this comparison, averaging 77.9 versus 72.2. Inside this category, AA Terminal-Bench 2.1 is the benchmark that creates the most daylight between them.

Which is better for math, MiniMax M3 or Qwen3.7 Max?

Qwen3.7 Max has the edge for math in this comparison, averaging 97.1 versus 85.7. MiniMax M3 stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, MiniMax M3 or Qwen3.7 Max?

MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 69.7. Inside this category, AA Briefcase 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.