Skip to main content
BenchLM
Data

Kimi K2.5 (Reasoning) vs Qwen3.7 Max

Updated November 17, 2026. Rank says Qwen3.7 Max is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Qwen3.7 Max has the higher public point estimate, 60.78 versus 56.58. Their conditional score ranges overlap. These ranges do not establish rank confidence. 12 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Moonshot AI logo

Moonshot AI

56.58/100

Estimated · Public rank #69

Conditional range 42.2–70.9

Model B
Alibaba logo

Alibaba

60.78/100

Supported · Public rank #50

90% interval 50.6–71.0

API price per 1M tokens

Kimi K2.5 (Reasoning): $0.60 input / $3 output

Qwen3.7 Max: No comparable API price

Context window

Kimi K2.5 (Reasoning): 256K

Qwen3.7 Max: 1M

Released

Kimi K2.5 (Reasoning): January 27, 2026

Qwen3.7 Max: May 16, 2026

Shared results
12
Kimi K2.5 (Reasoning) only
8
Qwen3.7 Max only
31
Like-for-like categories
2 / 8
Estimated: Kimi K2.5 (Reasoning) · Supported: Qwen3.7 Max. Conditional ranges do not establish rank confidence.How 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.

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Qwen3.7 Max

    Qwen3.7 Max has the higher public agentic point estimate, 40.1 to 34, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Qwen3.7 Max

    Qwen3.7 Max 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 (Reasoning) is scored on Estimated evidence for coding, 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.

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

34.8Kimi K2.5 (Reasoning)44.8Qwen3.7 Max

Directional only · BenchAlign v5.8

Qwen3.7 Max 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.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

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, reasoning, multimodal, 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.

Agentic

Like-for-like
Kimi K2.5 (Reasoning)
34.0
Supported · #93/138
Qwen3.7 Max
40.1
Supported · #75/138
Basis
BenchAlign v5.8 lane · 5 vs 10 public rows
Reading
Qwen3.7 Max leads · intervals overlap

Knowledge

Like-for-like
Kimi K2.5 (Reasoning)
52.2
Supported · #69/181
Qwen3.7 Max
60.2
Supported · #48/181
Basis
BenchAlign v5.8 lane · 4 vs 9 public rows
Reading
Qwen3.7 Max leads · intervals overlap

Coding

Directional only
Kimi K2.5 (Reasoning)
34.8
Estimated · #95/163
Qwen3.7 Max
44.8
Supported · #62/163
Basis
BenchAlign v5.8 lane · 6 vs 10 public rows
Reading
Directional only

Reasoning

Not comparable
Kimi K2.5 (Reasoning)
Not ranked
Qwen3.7 Max
51.7
Supported · #48/160
Basis
BenchAlign v5.8 lane · 1 vs 2 public rows
Reading
Not comparable

Multimodal

Not comparable
Kimi K2.5 (Reasoning)
53.4
Estimated · #47/67
Qwen3.7 Max
Not ranked
Basis
BenchAlign v5.8 lane · 2 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Kimi K2.5 (Reasoning)
Not ranked
Qwen3.7 Max
100.0
#1/17
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Kimi K2.5 (Reasoning)
Not ranked
Qwen3.7 Max
92.8
#17/157
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
Kimi K2.5 (Reasoning)
Not ranked
Qwen3.7 Max
78.3
#2/12
Basis
Provisional lane · 0 vs 3 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, 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 (Reasoning)
$0.0021
Fits in one request
Qwen3.7 Max
API rate not published
Fits in one request

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

Repository review

50K fresh input + 3K output tokens

Kimi K2.5 (Reasoning)
$0.039
Fits in one request
Qwen3.7 Max
API rate not published
Fits in one request

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

Cache-heavy agent loop

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

Kimi K2.5 (Reasoning)
$0.162
Fits in one request
Cached input priced at the published list-input rate
Qwen3.7 Max
API rate not published
Fits in one request
Cached-input rate unavailable

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

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

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 17, 2026.

Kimi K2.5 (Reasoning)

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 4 cheaper models score at least as high as Kimi K2.5 (Reasoning). The nearest is DeepSeek V4.1 Flash 1017 (score 64.4, $1.20 per 1M output tokens).
  • Qwen3.7 Max has no public API price, so it is not plotted.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Kimi K2.5 (Reasoning) on the full price vs performance chart

Specification differences

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

Context window

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

Kimi K2.5 (Reasoning)

256K

Qwen3.7 Max

1M

API model ID

Kimi K2.5 (Reasoning)

Not sourced

Qwen3.7 Max

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 (Reasoning)

Not published

Qwen3.7 Max

No comparable hosted API rate

Provider availability

Kimi K2.5 (Reasoning)

Not sourced

Qwen3.7 Max

Not sourced

Reasoning profile

Kimi K2.5 (Reasoning)

Reasoning

Qwen3.7 Max

Reasoning

Weight access

Kimi K2.5 (Reasoning)

Open Weight

Qwen3.7 Max

Proprietary

License

Kimi K2.5 (Reasoning)

Open Weight

Qwen3.7 Max

Proprietary

Release date

Kimi K2.5 (Reasoning)

2026-01-27

Qwen3.7 Max

2026-05-16

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 Max has the higher public point estimate, 60.78 versus 56.58. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Qwen3.7 Max 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 (Reasoning) or Qwen3.7 Max?

Qwen3.7 Max has the higher public point estimate, 60.78 versus 56.58. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Kimi K2.5 (Reasoning) or Qwen3.7 Max?

Qwen3.7 Max scores higher for coding on the public lane, 44.8 to 34.8. Kimi K2.5 (Reasoning) is 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 (Reasoning) or Qwen3.7 Max?

Qwen3.7 Max has the higher public agentic tasks point estimate, 40.1 to 34, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Kimi K2.5 (Reasoning) or Qwen3.7 Max?

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 (Reasoning) or Qwen3.7 Max?

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

Benchmark evidence

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

Browse raw public benchmark evidence51 rows

Agentic

  • Terminal-Bench 2.0

    Kimi K2.5 (Reasoning)50.8%
    Source
    Qwen3.7 Max69.7%
    Source

    Qwen3.7 Max leads this result

  • BrowseComp

    Kimi K2.5 (Reasoning)60.6%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • OSWorld-Verified

    Kimi K2.5 (Reasoning)63.3%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • Kimi K2.5 (Reasoning)32.58%
    Qwen3.7 Max64.27%

    Qwen3.7 Max leads this result

  • Terminal-Bench 2.1 (Vals)

    Kimi K2.5 (Reasoning)41.9%
    Source
    Qwen3.7 Max61.0%
    Source

    Qwen3.7 Max leads this result

  • QwenClawBench

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max64.3%
    Source

    Not directly comparable

  • Claw-Eval

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max65.2%
    Source

    Not directly comparable

  • BFCL v4

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max75.0%
    Source

    Not directly comparable

  • MCP Atlas

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max76.4%
    Source

    Not directly comparable

  • VITA-Bench

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max47.9%
    Source

    Not directly comparable

  • HLE w/ tools

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max53.5%
    Source

    Not directly comparable

  • ResearchClawBench

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max18.7%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Kimi K2.5 (Reasoning)76.8%
    Source
    Qwen3.7 Max80.4%
    Source

    Qwen3.7 Max leads this result

  • LiveCodeBench v6

    Kimi K2.5 (Reasoning)85.0%
    Source
    Qwen3.7 Max91.6%
    Source

    Qwen3.7 Max leads this result

  • Terminal-Bench 2.0

    Kimi K2.5 (Reasoning)50.8%
    Source
    Qwen3.7 Max69.7%
    Source

    Qwen3.7 Max leads this result

  • Vibe Code Bench

    Kimi K2.5 (Reasoning)17.54%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • LiveCodeBench (Vals)

    Kimi K2.5 (Reasoning)83.9%
    Source
    Qwen3.7 Max87.1%
    Source

    Qwen3.7 Max leads this result

  • SWE-bench (Vals)

    Kimi K2.5 (Reasoning)70.0%
    Source
    Qwen3.7 Max68.8%
    Source

    Kimi K2.5 (Reasoning) leads this result

  • SWE-bench Pro

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max60.6%
    Source

    Not directly comparable

  • SWE Multilingual

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max78.3%
    Source

    Not directly comparable

  • NL2Repo

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max47.2%
    Source

    Not directly comparable

  • SciCode

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max53.5%
    Source

    Not directly comparable

  • OpenHarmony Bench v1.0

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max53.4%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Kimi K2.5 (Reasoning)61%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • MRCRv2

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max90.4%
    Source

    Not directly comparable

  • CritPt

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max13.4%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Kimi K2.5 (Reasoning)78.5%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • CharXiv

    Kimi K2.5 (Reasoning)77.5%
    Source
    Qwen3.7 Max—

    Not directly comparable

Knowledge

  • GPQA

    Kimi K2.5 (Reasoning)87.6%
    Source
    Qwen3.7 Max92.4%
    Source

    Qwen3.7 Max leads this result

  • MMLU-Pro

    Kimi K2.5 (Reasoning)87.1%
    Source
    Qwen3.7 Max89.6%
    Source

    Qwen3.7 Max leads this result

  • GPQA Diamond (Vals)

    Kimi K2.5 (Reasoning)84.1%
    Source
    Qwen3.7 Max90.2%
    Source

    Qwen3.7 Max leads this result

  • MMLU-Pro (Vals)

    Kimi K2.5 (Reasoning)85.9%
    Source
    Qwen3.7 Max89.3%
    Source

    Qwen3.7 Max leads this result

  • GPQA-D

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max92.4%
    Source

    Not directly comparable

  • HLE

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max41.4%
    Source

    Not directly comparable

  • MMLU-Redux

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max95%
    Source

    Not directly comparable

  • SuperGPQA

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max73.6%
    Source

    Not directly comparable

  • MMMLU

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max90.3%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max87%
    Source

    Not directly comparable

  • NOVA-63

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max59.0%
    Source

    Not directly comparable

  • INCLUDE

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max86.2%
    Source

    Not directly comparable

  • MAXIFE

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max89.2%
    Source

    Not directly comparable

  • PolyMath

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max86.5%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max94.3%
    Source

    Not directly comparable

  • IFBench

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max79.1%
    Source

    Not directly comparable

Math

  • AIME 2025

    Kimi K2.5 (Reasoning)96.1%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • HMMT Feb 2025

    Kimi K2.5 (Reasoning)95.4%
    Source
    Qwen3.7 Max—

    Not directly comparable

  • HMMT Feb 2026

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max97.1%
    Source

    Not directly comparable

  • IMOAnswerBench

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max90.0%
    Source

    Not directly comparable

  • Apex

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max44.5%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max64.561%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Kimi K2.5 (Reasoning)—
    Qwen3.7 Max34.146%
    Source

    Not directly comparable

51 public results · 12 shared

Watch Kimi K2.5 (Reasoning) vs Qwen3.7 Max

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

Read a sample issue

Join 7,000+ subscribers.

Last updated November 17, 2026