Skip to main content
BenchLM
Advertise

Model comparison

MiniCPM5-1B vs Qwen3.7 Max

Data verified

Head-to-head evidence from 8 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
72.84/100
0 category wins3 category wins

Public leaderboard positions: MiniCPM5-1B unranked (Not scored); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniCPM5-1B and Qwen3.7 Max share 8 comparable benchmark results. 3 of 8 categories are comparable. 6 results are unique to MiniCPM5-1B; 50 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
8
MiniCPM5-1B only
6
Qwen3.7 Max only
50
Comparable categories
3 / 8

Treat this as a split decision. MiniCPM5-1B makes more sense if its workflow fits your team better; Qwen3.7 Max is the better fit if mathematics is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 8 shared benchmark results across 4 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

MiniCPM5-1B and Qwen3.7 Max finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Qwen3.7 Max gives you the larger context window at 1M, compared with 131K for MiniCPM5-1B.

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 MiniCPM5-1B and Qwen3.7 Max
CategoryMiniCPM5-1BΔQwen3.7 Max
MathMiniCPM5-1B33.1Margin→ 64.0Qwen3.7 Max97.1
Inst. FollowingMiniCPM5-1B58.5Margin→ 25.9Qwen3.7 Max84.4
KnowledgeMiniCPM5-1B44.0Margin→ 20.2Qwen3.7 Max64.2
AgenticMiniCPM5-1BNot measuredMarginNo overlapQwen3.7 Max69.7
CodingMiniCPM5-1BNot measuredMarginNo overlapQwen3.7 Max77.9
ReasoningMiniCPM5-1BNot measuredMarginNo overlapQwen3.7 Max90.4
MultilingualMiniCPM5-1BNot measuredMarginNo overlapQwen3.7 Max87.0

Decisive benchmark drivers

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

More
A · MiniCPM5-1BB · Qwen3.7 Max

  1. HMMT Feb 2026

    Math
    Source ↗
    A 25.8%B 97.1%
    Winner: Qwen3.7 MaxΔ 71.3
    HMMT Feb 2026: MiniCPM5-1B scored 25.8%; Qwen3.7 Max scored 97.1%. Qwen3.7 Max wins this benchmark.

  2. SuperGPQA

    Knowledge
    Source ↗
    A 23.1%B 73.6%
    Winner: Qwen3.7 MaxΔ 50.5
    SuperGPQA: MiniCPM5-1B scored 23.1%; Qwen3.7 Max scored 73.6%. Qwen3.7 Max wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 48.9%B 89.6%
    Winner: Qwen3.7 MaxΔ 40.7
    MMLU-Pro: MiniCPM5-1B scored 48.9%; Qwen3.7 Max scored 89.6%. Qwen3.7 Max wins this benchmark.

  4. IFBench

    Inst. Following
    Source ↗
    A 46.7%B 79.1%
    Winner: Qwen3.7 MaxΔ 32.4
    IFBench: MiniCPM5-1B scored 46.7%; Qwen3.7 Max scored 79.1%. Qwen3.7 Max wins this benchmark.

  5. IFEval

    Inst. Following
    Source ↗
    A 80.4%B 94.3%
    Winner: Qwen3.7 MaxΔ 13.9
    IFEval: MiniCPM5-1B scored 80.4%; Qwen3.7 Max scored 94.3%. Qwen3.7 Max wins this benchmark.

Operational comparison

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

MetricMiniCPM5-1BQwen3.7 MaxComparison
Input / output priceUSD per 1M tokensMiniCPM5-1BNot availableQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondMiniCPM5-1BNot availableQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniCPM5-1BNot availableQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniCPM5-1B131KQwen3.7 Max1MQwen3.7 Max lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
BFCL v4Source 25.1%75.0%Qwen3.7 Max leads
Terminal-Bench 2.0Source —69.7%Not comparable
QwenClawBenchSource —64.3%Not comparable
QwenWebBenchSource —1568Not comparable
Claw-EvalSource —65.2%Not comparable
MCP AtlasSource —76.4%Not comparable
VITA-BenchSource —47.9%Not comparable
HLE w/ toolsSource —53.5%Not comparable
AA Agentic IndexSource —30.6%Not comparable
τ²-bench resultsSource —94.7%Not comparable
GDPval-AASource —38.7%Not comparable
GDPval-AASource —1273Not comparable
Gert LabsSource —64.27%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
Coding
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
LiveCodeBench ProSource 22.7%—Not comparable
LiveCodeBench v6Source 33.5%—Not comparable
SWE-bench VerifiedSource —80.4%Not comparable
SWE-bench ProSource —60.6%Not comparable
SWE MultilingualSource —78.3%Not comparable
NL2RepoSource —47.2%Not comparable
SciCodeSource —53.5%Not comparable
LiveCodeBenchSource —91.6%Not comparable
Terminal-Bench 2.0Source —69.7%Not comparable
AA Coding IndexSource —66.0%Not comparable
AA-SciCodeSource —48.8%Not comparable
Reasoning
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
BBHSource 71.9%—Not comparable
MRCRv2Source —90.4%Not comparable
CritPtSource —13.4%Not comparable
AA-LCRSource —69.0%Not comparable
KnowledgeQwen3.7 Max wins
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
MMLU-ProSource 48.9%89.6%Qwen3.7 Max leads
MMLU-ReduxSource 70.1%95%Qwen3.7 Max leads
GPQA-DSource 26.3%92.4%Qwen3.7 Max leads
SuperGPQASource 23.1%73.6%Qwen3.7 Max leads
GPQASource —92.4%Not comparable
HLESource —41.4%Not comparable
MMMLUSource —90.3%Not comparable
Artificial Analysis Intelligence IndexSource —46.0%Not comparable
AA-GPQA DiamondSource —92.3%Not comparable
AA-HLESource —38.1%Not comparable
AA-Omniscience IndexSource —14.1%Not comparable
AA-Omniscience AccuracySource —30.1%Not comparable
AA-Omniscience Hallucination RateSource —22.9%Not comparable
MathQwen3.7 Max wins
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
AIME 2025Source 40.4%—Not comparable
AIME26Source 40.4%—Not comparable
HMMT Feb 2026Source 25.8%97.1%Qwen3.7 Max leads
MATH-500Source 91.6%—Not comparable
IMOAnswerBenchSource —90.0%Not comparable
ApexSource —44.5%Not comparable
Multilingual
BenchmarkMiniCPM5-1BQwen3.7 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
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
Design Arena WebsiteSource —1293Not comparable
Inst. FollowingQwen3.7 Max wins
BenchmarkMiniCPM5-1BQwen3.7 MaxResult
IFBenchSource 46.7%79.1%Qwen3.7 Max leads
IFEvalSource 80.4%94.3%Qwen3.7 Max leads
AA-IFBenchSource —80.5%Not comparable
Frequently Asked Questions (4)

Which is better, MiniCPM5-1B or Qwen3.7 Max?

MiniCPM5-1B and Qwen3.7 Max are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, MiniCPM5-1B or Qwen3.7 Max?

Qwen3.7 Max has the edge for knowledge tasks in this comparison, averaging 64.2 versus 44. Inside this category, GPQA-D is the benchmark that creates the most daylight between them.

Which is better for math, MiniCPM5-1B or Qwen3.7 Max?

Qwen3.7 Max has the edge for math in this comparison, averaging 97.1 versus 33.1. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.

Which is better for instruction following, MiniCPM5-1B or Qwen3.7 Max?

Qwen3.7 Max has the edge for instruction following in this comparison, averaging 84.4 versus 58.5. Inside this category, IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

OpenBMB 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.