Enter opens the highlighted result. Esc closes.

GLM 4.7 vs Kimi K2.5

GLM 4.7 leads Kimi K2.5 on coding, 55.1 to 38.6 on the Vibe Coding Index, and GLM 4.7 costs 1.3x less per output token ($2.20 vs $2.85 per million). Updated October 21, 2026; 70 benchmarks have a result for both.

Replace GLM 4.7 Replace Kimi K2.5
GLM 4.7Z.ai
Coding
55.1
Overall
56.9
Output $/M
$2.20
9
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
60
vs boards won of 70 shared, 1 tied

GLM 4.7 or Kimi K2.5: which to pick

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 38.6 for Kimi K2.5, though on 2 benchmarks against 3.

Pick Kimi K2.5 for a lower cost per solved task ($0.24 against $0.29) and a larger context window (262K against 205K tokens).

Model AGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
70
GLM 4.7 only
11
Kimi K2.5 only
29
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GLM 4.7 55.1 from 2 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Agentic work, 6.9 points apart on average over 6 shared benchmarks.
Widest single gap
CorpFin (Vals AI): GLM 4.7 46.4% against Kimi K2.5 68.3%, 21.9 points apart on a 0 to 100 scale.
Output price
GLM 4.7 $2.20 against Kimi K2.5 $2.85 per million output tokens, 1.3x apart.
Context window
GLM 4.7 takes 205K tokens, Kimi K2.5 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGLM 4.7BarsKimi K2.5Ties
Coding110
Intelligence02
Agentic work141 tie
Reasoning16
Math03
Knowledge38
Web design08
General319
All shared boards9601 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LMArena WebDev14351437Kimi K2.5
AA Coding Index45.346.8Kimi K2.5
LiveCodeBench (Vals AI)82.2%83.9%Kimi K2.5
SWE-bench Verified (Vals AI)69.4%70.0%Kimi K2.5
Vibe Code Bench (Vals AI)Not measured17.5%Only Kimi K2.5 measured
Code migration (Vals AI)Not measured7.0%Only Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured42.0%Only Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)89.4%Not measuredOnly GLM 4.7 measured
Terminal-Bench Hard (Artificial Analysis run)31.8%34.8%Kimi K2.5
Terminal-Bench33.4%43.2%Kimi K2.5
WeirdMLNot measured45.6%Only Kimi K2.5 measured
ALE-Bench399.5821.6Kimi K2.5
LMArena Text: coding14541483Kimi K2.5
LMArena Text: software and IT14531471Kimi K2.5
LMArena WebDev: React14201429Kimi K2.5
LMArena WebDev: HTML14471426GLM 4.7
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
AA Intelligence Index22.223.5Kimi K2.5
Epoch Capabilities Index143.6148.1Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack apps10501114Kimi K2.5
Design Arena: agents building mobile apps11051147Kimi K2.5
Design Arena: agents building Android apps11121118Kimi K2.5
Design Arena: agents building Godot games10581219Kimi K2.5
Finance Agent (Vals AI)Not measured35.8%Only Kimi K2.5 measured
Legal Research Bench (Vals AI)Not measured15.9%Only Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured28.5%Only Kimi K2.5 measured
τ²-Bench Telecom95.9%95.9%Tie
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2$2,377$1,198GLM 4.7
BrowseComp-Plus64.7%Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index16
Reasoning benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
GPQA Diamond80.0%84.1%Kimi K2.5
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)85.9%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)27.4%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)83.3%Not measuredOnly GLM 4.7 measured
ARC-AGINot measured65.3%Only Kimi K2.5 measured
ARC-AGI-2Not measured11.8%Only Kimi K2.5 measured
SimpleBench47.7%46.8%GLM 4.7
Chess puzzles21.0%Not measuredOnly GLM 4.7 measured
LMArena Text: hard prompts14431453Kimi K2.5
LMArena Text: expert14241466Kimi K2.5
LMArena Text: hard prompts in English14521460Kimi K2.5
LMArena Vision: diagramsNot measured1282Only Kimi K2.5 measured
LMArena Vision: homeworkNot measured1297Only Kimi K2.5 measured
Kagi LLM BenchmarkNot measured78.5%Only Kimi K2.5 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
AIME93.3%95.6%Kimi K2.5
MGSM (Vals AI)88.2%Not measuredOnly GLM 4.7 measured
AA Math Index95.0Not measuredOnly GLM 4.7 measured
AIME 2025 (Artificial Analysis run)95.0%Not measuredOnly GLM 4.7 measured
OTIS Mock AIME83.3%Not measuredOnly GLM 4.7 measured
ProofBench6.0%Not measuredOnly GLM 4.7 measured
LMArena Text: math14241470Kimi K2.5
LMArena Text: mathematical work14111473Kimi K2.5
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index38
Knowledge benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
MMLU Pro82.7%85.9%Kimi K2.5
LegalBench (Vals AI)83.4%Not measuredOnly GLM 4.7 measured
CaseLaw (Vals AI)54.9%58.7%Kimi K2.5
CorpFin (Vals AI)46.4%68.3%Kimi K2.5
TaxEval (Vals AI)68.8%74.2%Kimi K2.5
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)93.7%94.4%Kimi K2.5
MedCode (Vals AI)32.8%39.3%Kimi K2.5
MMLU Pro (Artificial Analysis run)85.6%Not measuredOnly GLM 4.7 measured
SimpleQA Verified32.2%34.3%Kimi K2.5
LMArena Text: science14571459Kimi K2.5
LMArena Text: medicine and healthcare14691448GLM 4.7
LMArena Text: legal and government14441441GLM 4.7
LMArena Text: business and finance14291427GLM 4.7
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
Design Arena: websites12261248Kimi K2.5
Design Arena: UI components11991236Kimi K2.5
Design Arena: game dev11891207Kimi K2.5
Design Arena: data viz11951219Kimi K2.5
Design Arena: 3D11911205Kimi K2.5
Design Arena: all code categories12171236Kimi K2.5
Design Arena: SVG11431149Kimi K2.5
Design Arena: ASCII art11651166Kimi K2.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index319
General benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
SAGE (Vals AI)Not measured49.9%Only Kimi K2.5 measured
MedScribe (Vals AI)68.6%76.4%Kimi K2.5
IFBench67.9%70.2%Kimi K2.5
Long context reasoning (AA-LCR)71.0%78.0%Kimi K2.5
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-bench15.9%19.3%Kimi K2.5
CL-bench Life10.9%13.2%Kimi K2.5
LMArena Text14351445Kimi K2.5
LMArena Text: instruction following14121431Kimi K2.5
LMArena Text: creative writing14011422Kimi K2.5
LMArena VisionNot measured1269Only Kimi K2.5 measured
LMArena Text: English14531453Kimi K2.5
LMArena Text: non-English14171433Kimi K2.5
LMArena Text: Chinese14951494GLM 4.7
LMArena Text: German14261441Kimi K2.5
LMArena Text: Japanese14391423GLM 4.7
LMArena Text: Korean13991412Kimi K2.5
LMArena Text: French14321454Kimi K2.5
LMArena Text: Spanish14341450Kimi K2.5
LMArena Text: Russian14231435Kimi K2.5
LMArena Text: Polish14351445Kimi K2.5
LMArena Text: multi-turn14461444GLM 4.7
LMArena Text: longer queries14321445Kimi K2.5
LMArena Text: writing and language14111425Kimi K2.5
LMArena Text: entertainment and media14001417Kimi K2.5
LMArena Vision: EnglishNot measured1274Only Kimi K2.5 measured
LMArena Vision: ChineseNot measured1328Only Kimi K2.5 measured
LMArena Vision: reading textNot measured1276Only Kimi K2.5 measured
LMArena Vision: humorNot measured1284Only Kimi K2.5 measured
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing thingsNot measured1285Only Kimi K2.5 measured
LMArena Vision: creative writingNot measured1269Only Kimi K2.5 measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.7 and Kimi K2.5
BenchmarkGLM 4.7Kimi K2.5Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GLM 4.7$0.0017Fits in one request
Kimi K2.5$0.0020Fits in one request

GLM 4.7 costs less

Repository review

50K input + 3K output tokens

GLM 4.7$0.037Fits in one request
Kimi K2.5$0.035Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

GLM 4.7$0.142Exceeds the context window
Kimi K2.5$0.135Fits in one request

Kimi K2.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GLM 4.7 and Kimi K2.5
SpecificationZ.ai GLM 4.7MoonshotAI Kimi K2.5
MakerZ.aiMoonshot AI
WeightsOpen weightsOpen weights
ReleasedDecember 22, 2025January 27, 2026
Context window205K262K
Input $/Mtok$0.60$0.532
Output $/Mtok$2.20$2.85
Coding index55.138.6
Independent measurements behind it23
Cost per solved task$0.29$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.7 better than Kimi K2.5 for coding?

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 38.6 for Kimi K2.5, though on 2 benchmarks against 3. Pick Kimi K2.5 for a lower cost per solved task ($0.24 against $0.29) and a larger context window (262K against 205K tokens).

Which is cheaper, GLM 4.7 or Kimi K2.5?

GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, GLM 4.7 costs $0.29 and Kimi K2.5 $0.24.

Which has the bigger context window, GLM 4.7 or Kimi K2.5?

Kimi K2.5, with 262K tokens against 205K.

How many benchmarks is the GLM 4.7 vs Kimi K2.5 comparison based on?

70 benchmarks have a result for both models as of October 21, 2026. GLM 4.7's coding index rests on 2 independent benchmarks and Kimi K2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/glm-4-7-vs-kimi-k2-5" title="GLM 4.7 vs Kimi K2.5, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/glm-4-7-vs-kimi-k2-5">LLMBenchmark.ai, GLM 4.7 vs Kimi K2.5</a></p>