Skip to main content

Model comparison

Kimi K3 vs Qwen3.7 Max

Data verified

Head-to-head evidence from 25 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Moonshot AI
80.96/100
Margin
8.1pts
← winning
72.84/100
1 category wins1 category wins

Public leaderboard positions: Kimi K3 #4 (Supported); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K3 and Qwen3.7 Max share 25 comparable benchmark results. 2 of 8 categories are comparable. 32 results are unique to Kimi K3; 33 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
25
Kimi K3 only
32
Qwen3.7 Max only
33
Comparable categories
2 / 8

Pick Kimi K3 if you want the stronger benchmark profile. Qwen3.7 Max only becomes the better choice if knowledge is the priority.

Confidence note. This is a partial-evidence comparison with 25 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

Kimi K3 is clearly ahead on the BenchAlign aggregate, 80.96 to 72.84. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K3's sharpest advantage is in agentic, where it averages 89.5 against 69.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 88.3% to 69.7%. Qwen3.7 Max does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Kimi K3 gives you the larger context window at 1.05M, compared with 1M for Qwen3.7 Max.

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 Kimi K3 and Qwen3.7 Max
CategoryKimi K3ΔQwen3.7 Max
AgenticKimi K389.5Margin 19.8Qwen3.7 Max69.7
KnowledgeKimi K361.0Margin 3.2Qwen3.7 Max64.2
CodingKimi K3Not measuredMarginNo overlapQwen3.7 Max77.9
ReasoningKimi K3Not measuredMarginNo overlapQwen3.7 Max90.4
MathKimi K3Not measuredMarginNo overlapQwen3.7 Max97.1
MultilingualKimi K3Not measuredMarginNo overlapQwen3.7 Max87.0
MultimodalKimi K378.5MarginNo overlapQwen3.7 MaxNot measured
Inst. FollowingKimi K3Not measuredMarginNo overlapQwen3.7 Max84.4

Decisive benchmark drivers

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

More
A · Kimi K3B · Qwen3.7 Max
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 88.3%B 69.7%
    Winner: Kimi K3Δ 18.6
    Terminal-Bench 2.0: Kimi K3 scored 88.3%; Qwen3.7 Max scored 69.7%. Kimi K3 wins this benchmark.
  2. HLE

    Knowledge
    Source ↗
    A 56%B 41.4%
    Winner: Kimi K3Δ 14.6
    HLE: Kimi K3 scored 56%; Qwen3.7 Max scored 41.4%. Kimi K3 wins this benchmark.
  3. GPQA

    Knowledge
    Source ↗
    A 93.5%B 92.4%
    Winner: Kimi K3Δ 1.1
    GPQA: Kimi K3 scored 93.5%; Qwen3.7 Max scored 92.4%. Kimi K3 wins this benchmark.

Operational comparison

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

MetricKimi K3Qwen3.7 MaxComparison
Input / output priceUSD per 1M tokensKimi K3$3 input / $15 outputQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondKimi K3Not availableQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K3Not availableQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K31.05MQwen3.7 Max1MKimi K3 lists the larger context window.

Benchmark Deep Dive

AgenticKimi K3 wins
BenchmarkKimi K3Qwen3.7 MaxResult
Terminal-Bench 2.0Source 88.3%69.7%Kimi K3 leads
BrowseCompSource 91.2%Not comparable
DeepSearchQASource 95.0%Not comparable
Toolathlon-VerifiedSource 73.2%Not comparable
MCP AtlasSource 84.2%76.4%Kimi K3 leads
AutomationBenchSource 30.8%Not comparable
JobBenchSource 52.9%Not comparable
APEX-AgentsSource 37.6%Not comparable
SpreadsheetBench 2Source 34.8%Not comparable
DECK-BenchSource 73.5%Not comparable
AA Agentic IndexSource 50.1%30.6%Kimi K3 leads
GDPval-AASource 59.0%38.7%Kimi K3 leads
GDPval-AASource 16791273Kimi K3 leads
AA BriefcaseSource 1543908Kimi K3 leads
AA AutomationBenchSource 52.7%25.6%Kimi K3 leads
AA EnterpriseOps-GymSource 45.3%45.0%Kimi K3 leads
AA Harvey LABSource 94.6%83.4%Kimi K3 leads
AA Tau3 BankingSource 33.4%Not comparable
aaTerminalBench21Source 85%74.5%Kimi K3 leads
APEX-Agents-AASource 41.3%Not comparable
AA ITBenchSource 47.7%42.5%Kimi K3 leads
QwenClawBenchSource 64.3%Not comparable
QwenWebBenchSource 1568Not comparable
Claw-EvalSource 65.2%Not comparable
BFCL v4Source 75.0%Not comparable
VITA-BenchSource 47.9%Not comparable
HLE w/ toolsSource 53.5%Not comparable
τ²-bench resultsSource 94.7%Not comparable
Gert LabsSource 64.27%Not comparable
ResearchClawBenchSource 18.7%Not comparable
terminalBenchHardSource 50.8%Not comparable
Coding
BenchmarkKimi K3Qwen3.7 MaxResult
deepSweSource 67.5%Not comparable
FrontierSWESource 81.2%Not comparable
ProgramBenchSource 77.8%Not comparable
Kimi Code Bench v2Source 72.9%Not comparable
sweMarathonSource 42%Not comparable
PostTrain BenchSource 36.6%Not comparable
MLS-Bench LiteSource 48.3%Not comparable
AA Coding IndexSource 76.2%66.0%Kimi K3 leads
AA-SciCodeSource 58.7%48.8%Kimi K3 leads
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
Reasoning
BenchmarkKimi K3Qwen3.7 MaxResult
AA-LCRSource 74.7%69.0%Kimi K3 leads
CritPtSource 23.4%13.4%Kimi K3 leads
MRCRv2Source 90.4%Not comparable
KnowledgeQwen3.7 Max wins
BenchmarkKimi K3Qwen3.7 MaxResult
GPQASource 93.5%92.4%Kimi K3 leads
GPQA-DSource 93.5%92.4%Kimi K3 leads
HLESource 56%41.4%Kimi K3 leads
HLE w/o toolsSource 43.5%Not comparable
Artificial Analysis Intelligence IndexSource 57.1%46.0%Kimi K3 leads
AA-GPQA DiamondSource 93.5%92.3%Kimi K3 leads
AA-HLESource 44.3%38.1%Kimi K3 leads
AA-Omniscience IndexSource 18.4%14.1%Kimi K3 leads
AA-Omniscience AccuracySource 46.0%30.1%Kimi K3 leads
AA-Omniscience Hallucination RateSource 50.9%22.9%Qwen3.7 Max leads
MMLU-ProSource 89.6%Not comparable
MMLU-ReduxSource 95%Not comparable
SuperGPQASource 73.6%Not comparable
MMMLUSource 90.3%Not comparable
Math
BenchmarkKimi K3Qwen3.7 MaxResult
HMMT Feb 2026Source 97.1%Not comparable
IMOAnswerBenchSource 90.0%Not comparable
ApexSource 44.5%Not comparable
Multilingual
BenchmarkKimi K3Qwen3.7 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
BenchmarkKimi K3Qwen3.7 MaxResult
OfficeQA ProSource 63.3%Not comparable
MMMU-ProSource 81.6%Not comparable
MMMU-Pro w/ PythonSource 83.4%Not comparable
CharXiv w/o toolsSource 84.8%Not comparable
CharXivSource 91.3%Not comparable
MathVisionSource 94.3%Not comparable
MathVision w/ PythonSource 97.8%Not comparable
BabyVision w/ PythonSource 85.7%Not comparable
ZeroBenchSource 23.0%Not comparable
ZeroBench w/ PythonSource 41.0%Not comparable
WorldVQA ForceAnswerSource 51.0%Not comparable
OmniDocBenchSource 91.1%Not comparable
PerceptionBenchSource 58.5%Not comparable
AA-MMMU-ProSource 80.5%Not comparable
Design Arena WebsiteSource 13861293Kimi K3 leads
Inst. Following
BenchmarkKimi K3Qwen3.7 MaxResult
IFEvalSource 94.3%Not comparable
IFBenchSource 79.1%Not comparable
AA-IFBenchSource 80.5%Not comparable
Frequently Asked Questions (3)

Which is better, Kimi K3 or Qwen3.7 Max?

Kimi K3 is ahead on BenchLM's BenchAlign leaderboard, 80.96 to 72.84. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 88.3% and 69.7%.

Which is better for knowledge tasks, Kimi K3 or Qwen3.7 Max?

Qwen3.7 Max has the edge for knowledge tasks in this comparison, averaging 64.2 versus 61. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K3 or Qwen3.7 Max?

Kimi K3 has the edge for agentic tasks in this comparison, averaging 89.5 versus 69.7. Inside this category, AA Briefcase 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.