Kimi K2.5 vs Qwen3.7 Plus

Updated October 20, 2026. Rank says Qwen3.7 Plus is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

Qwen3.7 Plus has the higher public score estimate, 53.74 versus 53.03, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 36 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Kimi K2.5

Moonshot AI

53.03/100

Supported · Public rank #82

90% interval 44.4–61.6

Model B

Qwen3.7 Plus

Alibaba

53.74/100

Supported · Public rank #77

90% interval 42.7–64.8

Shared results: 36
Kimi K2.5 only: 32
Qwen3.7 Plus only: 17
Like-for-like categories: 2 / 8

Supported: Kimi K2.5 and Qwen3.7 PlusHow the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Long documents
Prompts that approach the documented context limit
Qwen3.7 Plus
Qwen3.7 Plus has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Kimi K2.5 and Qwen3.7 Plus are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Kimi K2.5 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

38.5Kimi K2.540.3Qwen3.7 Plus

Directional only · BenchAlign v5.8

Qwen3.7 Plus has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Terminal-Bench 2.0Agentic
Normalized gap 19.5
Kimi K2.5:50.8%
Qwen3.7 Plus:70.3%
Kimi K2.5 source Qwen3.7 Plus source
OSWorld-VerifiedAgentic
Normalized gap 10.0
Kimi K2.5:63.3%
Qwen3.7 Plus:73.3%
Kimi K2.5 source Qwen3.7 Plus source
CharXivMultimodal
Normalized gap 8.4
Kimi K2.5:77.5%
Qwen3.7 Plus:85.9%
Kimi K2.5 source Qwen3.7 Plus source
SWE-bench ProCoding
Normalized gap 6.9
Kimi K2.5:50.7%
Qwen3.7 Plus:57.6%
Kimi K2.5 source Qwen3.7 Plus source
HMMT Feb 2026Math
Normalized gap 5.8
Kimi K2.5:87.1%
Qwen3.7 Plus:92.9%
Kimi K2.5 source Qwen3.7 Plus source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Multimodal

Like-for-like

Kimi K2.5: 70.4; #33/55
Qwen3.7 Plus: 82.0; #16/55
Basis: Provisional lane · 2 vs 2 weighted rows
Reading: Qwen3.7 Plus leads

Multilingual

Like-for-like

Kimi K2.5: 87.3; #8/17
Qwen3.7 Plus: 95.7; #3/17
Basis: Provisional lane · 1 vs 1 weighted rows
Reading: Qwen3.7 Plus leads

Agentic

Directional only

Kimi K2.5: 40.9; Estimated · #67/131
Qwen3.7 Plus: 35.1; Supported · #83/131
Basis: BenchAlign v5.8 lane · 16 vs 11 public rows
Reading: Directional only

Coding

Directional only

Kimi K2.5: 38.5; Estimated · #69/152
Qwen3.7 Plus: 40.3; Estimated · #66/152
Basis: BenchAlign v5.8 lane · 10 vs 7 public rows
Reading: Directional only

Knowledge

Directional only

Kimi K2.5: 51.4; Estimated · #78/187
Qwen3.7 Plus: 53.7; Estimated · #67/187
Basis: BenchAlign v5.8 lane · 8 vs 7 public rows
Reading: Directional only

Instruction following

Directional only

Kimi K2.5: 85.8; #48/149
Qwen3.7 Plus: 92.8; #17/149
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Directional only

Reasoning

Not comparable

Kimi K2.5: 71.3; Unranked · 3 rankable rows
Qwen3.7 Plus: 80.0; Unranked · 3 rankable rows
Basis: Provisional lane · 1 vs 1 weighted rows
Reading: Not comparable

Math

Not comparable

Kimi K2.5: 83.3; Unranked · 7 rankable rows
Qwen3.7 Plus: 64.3; Unranked · 4 rankable rows
Basis: Provisional lane · 2 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Kimi K2.5 and Qwen3.7 Plus
Category	Kimi K2.5	Qwen3.7 Plus	Basis	Reading
Multimodal	70.4#33/55	82.0#16/55	Like-for-likeProvisional lane · 2 vs 2 weighted rows	Qwen3.7 Plus leads
Multilingual	87.3#8/17	95.7#3/17	Like-for-likeProvisional lane · 1 vs 1 weighted rows	Qwen3.7 Plus leads
Agentic	40.9Estimated · #67/131	35.1Supported · #83/131	Directional onlyBenchAlign v5.8 lane · 16 vs 11 public rows	Directional only
Coding	38.5Estimated · #69/152	40.3Estimated · #66/152	Directional onlyBenchAlign v5.8 lane · 10 vs 7 public rows	Directional only
Knowledge	51.4Estimated · #78/187	53.7Estimated · #67/187	Directional onlyBenchAlign v5.8 lane · 8 vs 7 public rows	Directional only
Instruction following	85.8#48/149	92.8#17/149	Directional onlyProvisional lane · 0 vs 1 weighted rows	Directional only
Reasoning	71.3Unranked · 3 rankable rows	80.0Unranked · 3 rankable rows	Not comparableProvisional lane · 1 vs 1 weighted rows	Not comparable
Math	83.3Unranked · 7 rankable rows	64.3Unranked · 4 rankable rows	Not comparableProvisional lane · 2 vs 2 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Kimi K2.5: $0.0021; Fits in one request
Qwen3.7 Plus: API rate not published; Fits in one request

Qwen3.7 Plus has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Kimi K2.5: $0.039; Fits in one request
Qwen3.7 Plus: API rate not published; Fits in one request

Qwen3.7 Plus has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Kimi K2.5: $0.162; Fits in one request; Cached input priced at the published list-input rate
Qwen3.7 Plus: API rate not published; Fits in one request; Cached-input rate unavailable

Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.7 Plus has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationKimi K2.5Qwen3.7 Plus

Context window

Maximum documented context; output-token limits may be lower.

Kimi K2.5

256K

Qwen3.7 Plus

API model ID

Kimi K2.5

Not sourced

Qwen3.7 Plus

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Kimi K2.5

Not published

Qwen3.7 Plus

No comparable hosted API rate

Documented inputs

Kimi K2.5

Not sourced

Qwen3.7 Plus

Not sourced

Documented outputs

Kimi K2.5

Not sourced

Qwen3.7 Plus

Not sourced

Provider availability

Kimi K2.5

Not sourced

Qwen3.7 Plus

Not sourced

Reasoning profile

Kimi K2.5

Non-Reasoning

Qwen3.7 Plus

Reasoning

Weight access

Kimi K2.5

Open Weight

Qwen3.7 Plus

Proprietary

License

Kimi K2.5

Open Weight

Qwen3.7 Plus

Proprietary

Release date

Kimi K2.5

2026-01-27

Qwen3.7 Plus

2026-06-03

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: Qwen3.7 Plus has the higher public score estimate, 53.74 versus 53.03, but the 90% score intervals overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Qwen3.7 Plus has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Kimi K2.5 or Qwen3.7 Plus?

Qwen3.7 Plus has the higher public score estimate, 53.74 versus 53.03, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Kimi K2.5 or Qwen3.7 Plus?

Qwen3.7 Plus scores higher for coding on the public lane, 40.3 to 38.5. Kimi K2.5 and Qwen3.7 Plus are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Kimi K2.5 or Qwen3.7 Plus?

Kimi K2.5 scores higher for agentic tasks on the public lane, 40.9 to 35.1. Kimi K2.5 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Kimi K2.5 or Qwen3.7 Plus?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Kimi K2.5 or Qwen3.7 Plus?

Qwen3.7 Plus has the larger documented context window: 1M, compared with 256K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Kimi K2.5

API / mo$2,700

Self-host / mo$7,358

Break-even186M/day

Qwen3.7 Plus

API / mo$0

Self-host / moNot listed

Break-even—

Proprietary model — self-hosting not applicable.

Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence85 rows

Agentic

Terminal-Bench 2.0
Kimi K2.550.8%
Source
Qwen3.7 Plus70.3%
Source
Qwen3.7 Plus leads this result
BrowseComp
Kimi K2.560.6%
Source
Qwen3.7 Plus—
Not directly comparable
OSWorld-Verified
Kimi K2.563.3%
Source
Qwen3.7 Plus73.3%
Source
Qwen3.7 Plus leads this result
Claw-Eval
Kimi K2.552.3%
Source
Qwen3.7 Plus62.7%
Source
Qwen3.7 Plus leads this result
QwenClawBench
Kimi K2.554.3%
Source
Qwen3.7 Plus61.8%
Source
Qwen3.7 Plus leads this result
τ³-bench results
Kimi K2.565.7%
Source
Qwen3.7 Plus—
Not directly comparable
DeepSearchQA
Kimi K2.577.1%
Source
Qwen3.7 Plus—
Not directly comparable
DeepPlanning
Kimi K2.514.4%
Source
Qwen3.7 Plus62.3%
Source
Qwen3.7 Plus leads this result
Toolathlon
Kimi K2.527.8%
Source
Qwen3.7 Plus—
Not directly comparable
MCP Atlas
Kimi K2.529.5%
Source
Qwen3.7 Plus73.2%
Source
Qwen3.7 Plus leads this result
MCP-Tasks
Kimi K2.559.1%
Source
Qwen3.7 Plus—
Not directly comparable
WideResearch
Kimi K2.572.7%
Source
Qwen3.7 Plus—
Not directly comparable
BFCL v4
Kimi K2.568.3%
Source
Qwen3.7 Plus72.9%
Source
Qwen3.7 Plus leads this result
Gert Labs
Kimi K2.545.88%
Source
Qwen3.7 Plus—
Not directly comparable
ResearchClawBench
Kimi K2.514.0%
Source
Qwen3.7 Plus—
Not directly comparable
JobBench
Kimi K2.58.7%
Source
Qwen3.7 Plus—
Not directly comparable
VITA-Bench
Kimi K2.5—
Qwen3.7 Plus45.6%
Source
Not directly comparable
AndroidWorld
Kimi K2.5—
Qwen3.7 Plus81.0%
Source
Not directly comparable
OSWorld 2.0
Kimi K2.5—
Qwen3.7 Plus2.8%
Source
Not directly comparable
Terminal-Bench 2.1 (Vals)
Kimi K2.5—
Qwen3.7 Plus52.8%
Source
Not directly comparable

Coding

SWE-bench Verified
Kimi K2.576.8%
Source
Qwen3.7 Plus77.7%
Source
Qwen3.7 Plus leads this result
SWE-bench Verified*
Kimi K2.570.8%
Source
Qwen3.7 Plus—
Not directly comparable
LiveCodeBench v6
Kimi K2.585.0%
Source
Qwen3.7 Plus89.6%
Source
Qwen3.7 Plus leads this result
SWE-bench Pro
Kimi K2.550.7%
Source
Qwen3.7 Plus57.6%
Source
Qwen3.7 Plus leads this result
SWE Multilingual
Kimi K2.573%
Source
Qwen3.7 Plus75.8%
Source
Qwen3.7 Plus leads this result
SWE-Rebench
Kimi K2.558.5%
Source
Qwen3.7 Plus—
Not directly comparable
React Native Evals
Kimi K2.577.2%
Source
Qwen3.7 Plus—
Not directly comparable
NL2Repo
Kimi K2.532%
Source
Qwen3.7 Plus41.1%
Source
Qwen3.7 Plus leads this result
SciCode
Kimi K2.548.7%
Source
Qwen3.7 Plus51.3%
Source
Qwen3.7 Plus leads this result
Terminal-Bench 2.0
Kimi K2.550.8%
Source
Qwen3.7 Plus70.3%
Source
Qwen3.7 Plus leads this result

Reasoning

LongBench v2
Kimi K2.561%
Source
Qwen3.7 Plus—
Not directly comparable
CritPt
Kimi K2.5—
Qwen3.7 Plus9.1%
Source
Not directly comparable
MRCRv2
Kimi K2.5—
Qwen3.7 Plus91.7%
Source
Not directly comparable

Multimodal

MMMU
Kimi K2.584.3%
Source
Qwen3.7 Plus—
Not directly comparable
MMMU-Pro
Kimi K2.578.5%
Source
Qwen3.7 Plus79%
Source
Qwen3.7 Plus leads this result
RealWorldQA
Kimi K2.581.0%
Source
Qwen3.7 Plus86.9%
Source
Qwen3.7 Plus leads this result
OmniDocBench 1.5
Kimi K2.588.8%
Source
Qwen3.7 Plus91.4%
Source
Qwen3.7 Plus leads this result
Video-MME
Kimi K2.587.4%
Source
Qwen3.7 Plus—
Not directly comparable
Video-MME (with subtitle)
Kimi K2.587.4%
Source
Qwen3.7 Plus88.0%
Source
Qwen3.7 Plus leads this result
Video-MME (w/o subtitle)
Kimi K2.583.2%
Source
Qwen3.7 Plus—
Not directly comparable
MathVision
Kimi K2.584.2%
Source
Qwen3.7 Plus90.3%
Source
Qwen3.7 Plus leads this result
We-Math
Kimi K2.584.7%
Source
Qwen3.7 Plus—
Not directly comparable
DynaMath
Kimi K2.584.4%
Source
Qwen3.7 Plus—
Not directly comparable
SimpleVQA
Kimi K2.571.2%
Source
Qwen3.7 Plus81.7%
Source
Qwen3.7 Plus leads this result
MMLongBench-Doc
Kimi K2.558.5%
Source
Qwen3.7 Plus—
Not directly comparable
CC-OCR
Kimi K2.579.7%
Source
Qwen3.7 Plus—
Not directly comparable
AI2D_TEST
Kimi K2.590.8%
Source
Qwen3.7 Plus—
Not directly comparable
CountBench
Kimi K2.594.1%
Source
Qwen3.7 Plus—
Not directly comparable
RefCOCO (avg)
Kimi K2.587.8%
Source
Qwen3.7 Plus—
Not directly comparable
MMVU
Kimi K2.580.4%
Source
Qwen3.7 Plus—
Not directly comparable
VideoMMMU
Kimi K2.586.6%
Source
Qwen3.7 Plus85.4%
Source
Kimi K2.5 leads this result
MLVU (M-Avg)
Kimi K2.585.0%
Source
Qwen3.7 Plus87.4%
Source
Qwen3.7 Plus leads this result
CharXiv
Kimi K2.577.5%
Source
Qwen3.7 Plus85.9%
Source
Qwen3.7 Plus leads this result
ERQA
Kimi K2.5—
Qwen3.7 Plus69.8%
Source
Not directly comparable
MedXpertQA (MM)
Kimi K2.5—
Qwen3.7 Plus71.0%
Source
Not directly comparable
ScreenSpot Pro
Kimi K2.5—
Qwen3.7 Plus79.0%
Source
Not directly comparable
MMSearch-Plus
Kimi K2.5—
Qwen3.7 Plus41.4%
Source
Not directly comparable
OCRBench V2
Kimi K2.5—
Qwen3.7 Plus70.7%
Source
Not directly comparable
ODINW13
Kimi K2.5—
Qwen3.7 Plus51.1%
Source
Not directly comparable

Knowledge

GPQA
Kimi K2.587.6%
Source
Qwen3.7 Plus90.3%
Source
Qwen3.7 Plus leads this result
GPQA-D
Kimi K2.587.6%
Source
Qwen3.7 Plus90.3%
Source
Qwen3.7 Plus leads this result
SuperGPQA
Kimi K2.569.2%
Source
Qwen3.7 Plus71.4%
Source
Qwen3.7 Plus leads this result
MMLU-Pro
Kimi K2.587.1%
Source
Qwen3.7 Plus88.5%
Source
Qwen3.7 Plus leads this result
MMLU-Pro (Arcee)
Kimi K2.587.1%
Source
Qwen3.7 Plus—
Not directly comparable
MMLU-Redux
Kimi K2.594.5%
Source
Qwen3.7 Plus94.5%
Source
Tie
C-Eval
Kimi K2.594%
Source
Qwen3.7 Plus—
Not directly comparable
HLE
Kimi K2.530.1%
Source
Qwen3.7 Plus34.7%
Source
Qwen3.7 Plus leads this result
MMMLU
Kimi K2.5—
Qwen3.7 Plus89.0%
Source
Not directly comparable

Multilingual

MMLU-ProX
Kimi K2.582.3%
Source
Qwen3.7 Plus85.4%
Source
Qwen3.7 Plus leads this result
NOVA-63
Kimi K2.556.0%
Source
Qwen3.7 Plus58.8%
Source
Qwen3.7 Plus leads this result
INCLUDE
Kimi K2.583.3%
Source
Qwen3.7 Plus83.0%
Source
Kimi K2.5 leads this result
PolyMath
Kimi K2.543.1%
Source
Qwen3.7 Plus84.0%
Source
Qwen3.7 Plus leads this result
MAXIFE
Kimi K2.572.8%
Source
Qwen3.7 Plus88.8%
Source
Qwen3.7 Plus leads this result

Instruction following

IFEval
Kimi K2.593.9%
Source
Qwen3.7 Plus94.6%
Source
Qwen3.7 Plus leads this result
IFBench
Kimi K2.5—
Qwen3.7 Plus79.1%
Source
Not directly comparable

Math

AIME 2025
Kimi K2.596.1%
Source
Qwen3.7 Plus—
Not directly comparable
AIME26
Kimi K2.595.8%
Source
Qwen3.7 Plus—
Not directly comparable
AIME25 (Arcee)
Kimi K2.596.3%
Source
Qwen3.7 Plus—
Not directly comparable
HMMT Feb 2025
Kimi K2.595.4%
Source
Qwen3.7 Plus—
Not directly comparable
HMMT Nov 2025
Kimi K2.591.1%
Source
Qwen3.7 Plus—
Not directly comparable
HMMT Feb 2026
Kimi K2.587.1%
Source
Qwen3.7 Plus92.9%
Source
Qwen3.7 Plus leads this result
MMAnswerBench
Kimi K2.581.8%
Source
Qwen3.7 Plus—
Not directly comparable
IMOAnswerBench
Kimi K2.5—
Qwen3.7 Plus86.0%
Source
Not directly comparable
Apex
Kimi K2.5—
Qwen3.7 Plus22.7%
Source
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.5—
Qwen3.7 Plus34.386%
Source
Not directly comparable

85 public results · 36 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Kimi K2.5 vs Qwen3.7 Plus

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 5,600+ readers.

Last updated October 20, 2026

Kimi K2.5 vs Qwen3.7 Plus

Decision reading

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Multimodal

Multilingual

Agentic

Coding

Knowledge

Instruction following

Reasoning

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, Kimi K2.5 or Qwen3.7 Plus?

Which is better for coding, Kimi K2.5 or Qwen3.7 Plus?

Which is better for agentic tasks, Kimi K2.5 or Qwen3.7 Plus?

Which costs less, Kimi K2.5 or Qwen3.7 Plus?

Which has the larger context window, Kimi K2.5 or Qwen3.7 Plus?

Self-host vs API cost

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch Kimi K2.5 vs Qwen3.7 Plus