Enter opens the highlighted result. Esc closes.

GLM 5 vs Kimi K2.5

GLM 5 leads Kimi K2.5 on coding, 41.7 to 38.6 on the Vibe Coding Index, at about the same output price ($3.20 vs $2.85 per million). Updated October 21, 2026; 72 benchmarks have a result for both.

Replace GLM 5 Replace Kimi K2.5
GLM 5Z.ai
Coding
41.7
Overall
54.3
Output $/M
$3.20
38
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
34
vs boards won of 72 shared

GLM 5 or Kimi K2.5: which to pick

Pick GLM 5 for coding: it scores 41.7 on the Vibe Coding Index against 38.6 for Kimi K2.5.

Pick Kimi K2.5 for output tokens 1.1x cheaper ($2.85 vs $3.20 per million) and a lower cost per solved task ($0.24 against $0.63).

Model AGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
72
GLM 5 only
4
Kimi K2.5 only
27
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 5 41.7 from 3 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Agentic work, 6.3 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI: GLM 5 44.7% against Kimi K2.5 65.3%, 20.7 points apart on a 0 to 100 scale.
Output price
GLM 5 $3.20 against Kimi K2.5 $2.85 per million output tokens, 1.1x apart.
Context window
GLM 5 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 5BarsKimi K2.5Ties
Coding86
Intelligence11
Agentic work42
Reasoning19
Math03
Knowledge54
Web design53
General146
All shared boards3834
CodingLike-for-likeSix of these boards feed the Vibe Coding Index86
Coding benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
SWE-bench Verified72.8%70.8%GLM 5
SWE-bench Multilingual69.7%67.3%GLM 5
LMArena WebDev14351437Kimi K2.5
AA Coding IndexNot measured46.8Only Kimi K2.5 measured
LiveCodeBench (Vals AI)81.9%83.9%Kimi K2.5
SWE-bench Verified (Vals AI)71.4%70.0%GLM 5
Vibe Code Bench (Vals AI)23.4%17.5%GLM 5
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
Terminal-Bench Hard (Artificial Analysis run)43.2%34.8%GLM 5
Terminal-Bench52.4%43.2%GLM 5
WeirdML48.2%45.6%GLM 5
ALE-Bench765.6821.6Kimi K2.5
LMArena Text: coding14611483Kimi K2.5
LMArena Text: software and IT14601471Kimi K2.5
LMArena WebDev: React14241429Kimi K2.5
LMArena WebDev: HTML14501426GLM 5
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
AA Intelligence Index27.923.5GLM 5
Epoch Capabilities Index145.8148.1Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index42
Agentic work benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack apps11231114GLM 5
Design Arena: agents building mobile apps11361147Kimi K2.5
Design Arena: agents building Android apps11461118GLM 5
Design Arena: agents building Godot games11441219Kimi K2.5
Design Arena: HTML slides1148Not measuredOnly GLM 5 measured
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 Telecom98.2%95.9%GLM 5
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2$4,432$1,198GLM 5
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index19
Reasoning benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
GPQA Diamond83.3%84.1%Kimi K2.5
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)82.0%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)29.3%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)87.8%Not measuredOnly GLM 5 measured
ARC-AGI44.7%65.3%Kimi K2.5
ARC-AGI-24.9%11.8%Kimi K2.5
SimpleBench53.2%46.8%GLM 5
LMArena Text: hard prompts14521453Kimi K2.5
LMArena Text: expert14541466Kimi K2.5
LMArena Text: hard prompts in English14601460Kimi K2.5
LMArena Vision: diagramsNot measured1282Only Kimi K2.5 measured
LMArena Vision: homeworkNot measured1297Only Kimi K2.5 measured
Kagi LLM Benchmark75.0%78.5%Kimi K2.5
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
AIME91.7%95.6%Kimi K2.5
OTIS Mock AIME80.0%Not measuredOnly GLM 5 measured
LMArena Text: math14401470Kimi K2.5
LMArena Text: mathematical work14511473Kimi K2.5
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index54
Knowledge benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
MMLU Pro86.0%85.9%GLM 5
LegalBench (Vals AI)84.1%Not measuredOnly GLM 5 measured
CaseLaw (Vals AI)52.5%58.7%Kimi K2.5
CorpFin (Vals AI)62.9%68.3%Kimi K2.5
TaxEval (Vals AI)70.0%74.2%Kimi K2.5
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)94.3%94.4%Kimi K2.5
MedCode (Vals AI)Not measured39.3%Only Kimi K2.5 measured
SimpleQA VerifiedNot measured34.3%Only Kimi K2.5 measured
LMArena Text: science14601459GLM 5
LMArena Text: medicine and healthcare14551448GLM 5
LMArena Text: legal and government14531441GLM 5
LMArena Text: business and finance14301427GLM 5
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index53
Web design benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
Design Arena: websites12471248Kimi K2.5
Design Arena: UI components12301236Kimi K2.5
Design Arena: game dev12341207GLM 5
Design Arena: data viz12281219GLM 5
Design Arena: 3D12291205GLM 5
Design Arena: all code categories12461236GLM 5
Design Arena: SVG11681149GLM 5
Design Arena: ASCII art11471166Kimi K2.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index146
General benchmarks for GLM 5 and Kimi K2.5
BenchmarkGLM 5Kimi K2.5Leader
SAGE (Vals AI)Not measured49.9%Only Kimi K2.5 measured
MedScribe (Vals AI)Not measured76.4%Only Kimi K2.5 measured
IFBench72.3%70.2%GLM 5
Long context reasoning (AA-LCR)75.7%78.0%Kimi K2.5
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-bench18.7%19.3%Kimi K2.5
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text14461445GLM 5
LMArena Text: instruction following14281431Kimi K2.5
LMArena Text: creative writing14381422GLM 5
LMArena VisionNot measured1269Only Kimi K2.5 measured
LMArena Text: English14581453GLM 5
LMArena Text: non-English14301433Kimi K2.5
LMArena Text: Chinese15111494GLM 5
LMArena Text: German14471441GLM 5
LMArena Text: Japanese14161423Kimi K2.5
LMArena Text: Korean14231412GLM 5
LMArena Text: French14561454GLM 5
LMArena Text: Spanish14541450GLM 5
LMArena Text: Russian14361435GLM 5
LMArena Text: Polish14341445Kimi K2.5
LMArena Text: multi-turn14561444GLM 5
LMArena Text: longer queries14461445GLM 5
LMArena Text: writing and language14371425GLM 5
LMArena Text: entertainment and media14261417GLM 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 5 and Kimi K2.5
BenchmarkGLM 5Kimi 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 5$0.0026Fits in one request
Kimi K2.5$0.0020Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

GLM 5$0.060Fits in one request
Kimi K2.5$0.035Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

GLM 5$0.232Exceeds 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 5 and Kimi K2.5
SpecificationZ.ai GLM 5MoonshotAI Kimi K2.5
MakerZ.aiMoonshot AI
WeightsOpen weightsOpen weights
ReleasedFebruary 11, 2026January 27, 2026
Context window205K262K
Input $/Mtok$1.00$0.532
Output $/Mtok$3.20$2.85
Coding index41.738.6
Independent measurements behind it33
Cost per solved task$0.63$0.24
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick GLM 5 for coding: it scores 41.7 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 1.1x cheaper ($2.85 vs $3.20 per million) and a lower cost per solved task ($0.24 against $0.63).

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

GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, GLM 5 costs $0.63 and Kimi K2.5 $0.24.

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

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

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

72 benchmarks have a result for both models as of October 21, 2026. GLM 5's coding index rests on 3 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-5-vs-kimi-k2-5" title="GLM 5 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-5-vs-kimi-k2-5">LLMBenchmark.ai, GLM 5 vs Kimi K2.5</a></p>