Skip to main content
BenchLM
Advertise

Model comparison

Kimi K3 vs Qwen3.7 Plus

Data verified

Head-to-head evidence from 24 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K3
Moonshot AI
80.96/100
Margin
13.7pts
← winning
67.22/100
2 category wins1 category wins

Public leaderboard positions: Kimi K3 #4 (Supported); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K3 and Qwen3.7 Plus share 24 comparable benchmark results. 3 of 8 categories are comparable. 33 results are unique to Kimi K3; 45 to Qwen3.7 Plus.

Updated July 23, 2026
Shared results
24
Kimi K3 only
33
Qwen3.7 Plus only
45
Comparable categories
3 / 8

Pick Kimi K3 if you want the stronger benchmark profile. Qwen3.7 Plus only becomes the better choice if multimodal & grounded is the priority.

Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 5 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

Kimi K3 is clearly ahead on the BenchAlign aggregate, 80.96 to 67.22. 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 71.7. The single biggest benchmark swing on the page is HLE, 56% to 34.7%. Qwen3.7 Plus does hit back in multimodal & grounded, 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 Plus.

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 Plus
CategoryKimi K3ΔQwen3.7 Plus
AgenticKimi K389.5Margin← 17.8Qwen3.7 Plus71.7
MultimodalKimi K378.5Margin→ 3.0Qwen3.7 Plus81.5
KnowledgeKimi K361.0Margin← 0.9Qwen3.7 Plus60.1
CodingKimi K3Not measuredMarginNo overlapQwen3.7 Plus75.6
ReasoningKimi K3Not measuredMarginNo overlapQwen3.7 Plus91.7
MathKimi K3Not measuredMarginNo overlapQwen3.7 Plus92.9
MultilingualKimi K3Not measuredMarginNo overlapQwen3.7 Plus85.4
Inst. FollowingKimi K3Not measuredMarginNo overlapQwen3.7 Plus84.5

Decisive benchmark drivers

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

More
A · Kimi K3B · Qwen3.7 Plus

  1. HLE

    Knowledge
    Source ↗
    A 56%B 34.7%
    Winner: Kimi K3Δ 21.3
    HLE: Kimi K3 scored 56%; Qwen3.7 Plus scored 34.7%. Kimi K3 wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 88.3%B 70.3%
    Winner: Kimi K3Δ 18
    Terminal-Bench 2.0: Kimi K3 scored 88.3%; Qwen3.7 Plus scored 70.3%. Kimi K3 wins this benchmark.

  3. CharXiv

    Multimodal
    Source ↗
    A 91.3%B 85.9%
    Winner: Kimi K3Δ 5.4
    CharXiv: Kimi K3 scored 91.3%; Qwen3.7 Plus scored 85.9%. Kimi K3 wins this benchmark.

  4. GPQA

    Knowledge
    Source ↗
    A 93.5%B 90.3%
    Winner: Kimi K3Δ 3.2
    GPQA: Kimi K3 scored 93.5%; Qwen3.7 Plus scored 90.3%. Kimi K3 wins this benchmark.

  5. MMMU-Pro

    Multimodal
    Source ↗
    A 81.6%B 79%
    Winner: Kimi K3Δ 2.6
    MMMU-Pro: Kimi K3 scored 81.6%; Qwen3.7 Plus scored 79%. 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 PlusComparison
Input / output priceUSD per 1M tokensKimi K3$3 input / $15 outputQwen3.7 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondKimi K3Not availableQwen3.7 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K3Not availableQwen3.7 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K31.05MQwen3.7 Plus1MKimi K3 lists the larger context window.

Benchmark Deep Dive

AgenticKimi K3 wins
BenchmarkKimi K3Qwen3.7 PlusResult
Terminal-Bench 2.0Source 88.3%70.3%Kimi K3 leads
BrowseCompSource 91.2%—Not comparable
DeepSearchQASource 95.0%—Not comparable
Toolathlon-VerifiedSource 73.2%—Not comparable
MCP AtlasSource 84.2%73.2%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%20.8%Kimi K3 leads
GDPval-AASource 59.0%21.8%Kimi K3 leads
GDPval-AASource 1679936Kimi K3 leads
AA BriefcaseSource 1543—Not comparable
AA AutomationBenchSource 52.7%—Not comparable
AA EnterpriseOps-GymSource 45.3%—Not comparable
AA Harvey LABSource 94.6%—Not comparable
AA Tau3 BankingSource 33.4%—Not comparable
aaTerminalBench21Source 85%—Not comparable
APEX-Agents-AASource 41.3%22.4%Kimi K3 leads
AA ITBenchSource 47.7%—Not comparable
QwenClawBenchSource —61.8%Not comparable
QwenWebBenchSource —1536Not comparable
Claw-EvalSource —62.7%Not comparable
BFCL v4Source —72.9%Not comparable
VITA-BenchSource —45.6%Not comparable
DeepPlanningSource —62.3%Not comparable
OSWorld-VerifiedSource —73.3%Not comparable
AndroidWorldSource —81.0%Not comparable
τ²-bench resultsSource —93%Not comparable
OSWorld 2.0Source —2.8%Not comparable
Coding
BenchmarkKimi K3Qwen3.7 PlusResult
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%55.9%Kimi K3 leads
AA-SciCodeSource 58.7%45.5%Kimi K3 leads
Terminal-Bench 2.0Source —70.3%Not comparable
SWE-bench VerifiedSource —77.7%Not comparable
SWE-bench ProSource —57.6%Not comparable
SWE MultilingualSource —75.8%Not comparable
NL2RepoSource —41.1%Not comparable
SciCodeSource —51.3%Not comparable
LiveCodeBenchSource —89.6%Not comparable
Reasoning
BenchmarkKimi K3Qwen3.7 PlusResult
AA-LCRSource 74.7%65.0%Kimi K3 leads
CritPtSource 23.4%9.1%Kimi K3 leads
MRCRv2Source —91.7%Not comparable
KnowledgeKimi K3 wins
BenchmarkKimi K3Qwen3.7 PlusResult
GPQASource 93.5%90.3%Kimi K3 leads
GPQA-DSource 93.5%90.3%Kimi K3 leads
HLESource 56%34.7%Kimi K3 leads
HLE w/o toolsSource 43.5%—Not comparable
Artificial Analysis Intelligence IndexSource 57.1%39.0%Kimi K3 leads
AA-GPQA DiamondSource 93.5%90.0%Kimi K3 leads
AA-HLESource 44.3%33.4%Kimi K3 leads
AA-Omniscience IndexSource 18.4%2.4%Kimi K3 leads
AA-Omniscience AccuracySource 46.0%22.2%Kimi K3 leads
AA-Omniscience Hallucination RateSource 50.9%25.5%Qwen3.7 Plus leads
MMLU-ProSource —88.5%Not comparable
MMLU-ReduxSource —94.5%Not comparable
SuperGPQASource —71.4%Not comparable
MMMLUSource —89.0%Not comparable
Math
BenchmarkKimi K3Qwen3.7 PlusResult
HMMT Feb 2026Source —92.9%Not comparable
IMOAnswerBenchSource —86.0%Not comparable
ApexSource —22.7%Not comparable
Multilingual
BenchmarkKimi K3Qwen3.7 PlusResult
MMLU-ProXSource —85.4%Not comparable
NOVA-63Source —58.8%Not comparable
INCLUDESource —83.0%Not comparable
MAXIFESource —88.8%Not comparable
PolyMathSource —84.0%Not comparable
MultimodalQwen3.7 Plus wins
BenchmarkKimi K3Qwen3.7 PlusResult
OfficeQA ProSource 63.3%—Not comparable
MMMU-ProSource 81.6%79%Kimi K3 leads
MMMU-Pro w/ PythonSource 83.4%—Not comparable
CharXiv w/o toolsSource 84.8%—Not comparable
CharXivSource 91.3%85.9%Kimi K3 leads
MathVisionSource 94.3%90.3%Kimi K3 leads
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%80.5%Tie
Design Arena WebsiteSource 13861288Kimi K3 leads
ERQASource —69.8%Not comparable
MedXpertQA (MM)Source —71.0%Not comparable
ScreenSpot ProSource —79.0%Not comparable
SimpleVQASource —81.7%Not comparable
MMSearch-PlusSource —41.4%Not comparable
RealWorldQASource —86.9%Not comparable
OmniDocBench 1.5Source —91.4%Not comparable
OCRBench V2Source —70.7%Not comparable
ODINW13Source —51.1%Not comparable
Video-MME (with subtitle)Source —88.0%Not comparable
VideoMMMUSource —85.4%Not comparable
MLVU (M-Avg)Source —87.4%Not comparable
Inst. Following
BenchmarkKimi K3Qwen3.7 PlusResult
IFEvalSource —94.6%Not comparable
IFBenchSource —79.1%Not comparable
AA-IFBenchSource —78.0%Not comparable
Frequently Asked Questions (4)

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

Kimi K3 is ahead on BenchLM's BenchAlign leaderboard, 80.96 to 67.22. The biggest single separator in this matchup is HLE, where the scores are 56% and 34.7%.

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

Kimi K3 has the edge for knowledge tasks in this comparison, averaging 61 versus 60.1. 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 Plus?

Kimi K3 has the edge for agentic tasks in this comparison, averaging 89.5 versus 71.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Kimi K3 or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 81.5 versus 78.5. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Moonshot AI 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.