Enter opens the highlighted result. Esc closes.

GLM 5 vs MiniMax M2.5

GLM 5 leads MiniMax M2.5 on coding, 41.7 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 2.7x less per output token ($1.20 vs $3.20 per million). Updated October 22, 2026; 69 benchmarks have a result for both.

Replace GLM 5 Replace MiniMax M2.5
GLM 5Z.ai
Coding
41.7
Overall
54.3
Output $/M
$3.20
62
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
6
vs boards won of 69 shared, 1 tied

GLM 5 or MiniMax M2.5: which to pick

Pick GLM 5 for coding: it scores 41.7 on the Vibe Coding Index against 37.2 for MiniMax M2.5.

Pick MiniMax M2.5 for output tokens 2.7x cheaper ($1.20 vs $3.20 per million) and a lower cost per solved task ($0.62 against $0.63).

Model AGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved taskModel BMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved task
Shared results
69
GLM 5 only
11
MiniMax M2.5 only
2
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, MiniMax M2.5 37.2 from 3 benchmarks.
Widest category
General, 15.6 points apart on average over 20 shared benchmarks.
Widest single gap
LMArena Text: Japanese: GLM 5 1416 against MiniMax M2.5 1171, 40.9 points apart on a 0 to 100 scale.
Output price
GLM 5 $3.20 against MiniMax M2.5 $1.20 per million output tokens, 2.7x apart.
Context window
Both take 205K tokens.

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 5BarsMiniMax M2.5Ties
Coding142
Intelligence11
Agentic work20
Reasoning621 tie
Math30
Knowledge91
Web design70
General200
All shared boards6261 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index142
Coding benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
SWE-bench Verified72.8%75.8%MiniMax M2.5
SWE-bench Multilingual69.7%68.3%GLM 5
LMArena WebDev14351386GLM 5
LiveCodeBench (Vals AI)81.9%79.2%GLM 5
SWE-bench Verified (Vals AI)71.4%74.2%MiniMax M2.5
Vibe Code Bench (Vals AI)23.4%14.8%GLM 5
Terminal-Bench Hard (Artificial Analysis run)43.2%34.8%GLM 5
Terminal-Bench52.4%42.7%GLM 5
WeirdML48.2%Not measuredOnly GLM 5 measured
ALE-Bench765.6618.2GLM 5
LMArena Text: coding14611380GLM 5
LMArena Text: software and IT14601383GLM 5
LMArena WebDev: React14241374GLM 5
LMArena WebDev: HTML14501414GLM 5
SWE Atlas: Codebase QnA20.5%10.3%GLM 5
SWE Atlas: Refactoring24.2%19.5%GLM 5
SWE Atlas: Test Writing28.7%18.6%GLM 5
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
AA Intelligence Index27.922.8GLM 5
Epoch Capabilities Index145.8146.6MiniMax M2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
Design Arena: agents building full-stack apps1123Not measuredOnly GLM 5 measured
Design Arena: agents building mobile apps1135Not measuredOnly GLM 5 measured
Design Arena: agents building Android apps1146Not measuredOnly GLM 5 measured
Design Arena: agents building Godot games1144Not measuredOnly GLM 5 measured
Design Arena: HTML slides1087Not measuredOnly GLM 5 measured
τ²-Bench Telecom98.2%95.3%GLM 5
Vending-Bench 2$4,432-$23GLM 5
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
Reasoning benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
GPQA Diamond83.3%82.1%GLM 5
GPQA Diamond (Artificial Analysis run)82.0%84.8%MiniMax M2.5
Humanity's Last Exam (Artificial Analysis run)29.3%20.5%GLM 5
GPQA Diamond (Epoch AI run)87.8%Not measuredOnly GLM 5 measured
ARC-AGI44.7%63.7%MiniMax M2.5
ARC-AGI-24.9%4.9%Tie
SimpleBench53.2%Not measuredOnly GLM 5 measured
LMArena Text: hard prompts14521372GLM 5
LMArena Text: expert14541378GLM 5
LMArena Text: hard prompts in English14601384GLM 5
Kagi LLM Benchmark75.0%55.2%GLM 5
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
AIME91.7%88.8%GLM 5
OTIS Mock AIME80.0%Not measuredOnly GLM 5 measured
ProofBenchNot measured4.0%Only MiniMax M2.5 measured
LMArena Text: math14401378GLM 5
LMArena Text: mathematical work14511378GLM 5
MathArena19.8%Not measuredOnly GLM 5 measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
Knowledge benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
MMLU Pro86.0%80.1%GLM 5
LegalBench (Vals AI)84.1%80.0%GLM 5
CaseLaw (Vals AI)52.5%53.5%MiniMax M2.5
CorpFin (Vals AI)62.9%59.6%GLM 5
TaxEval (Vals AI)70.0%68.2%GLM 5
MedQA (Vals AI)94.3%92.5%GLM 5
LMArena Text: science14601369GLM 5
LMArena Text: medicine and healthcare14551357GLM 5
LMArena Text: legal and government14531366GLM 5
LMArena Text: business and finance14301356GLM 5
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
Design Arena: websites12471222GLM 5
Design Arena: UI components12281170GLM 5
Design Arena: game dev12341176GLM 5
Design Arena: data viz12281172GLM 5
Design Arena: 3D12281170GLM 5
Design Arena: all code categories12461207GLM 5
Design Arena: SVG11671150GLM 5
Design Arena: ASCII art1147Not measuredOnly GLM 5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
General benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
IFBench72.3%71.6%GLM 5
Long context reasoning (AA-LCR)75.7%73.3%GLM 5
CL-bench18.7%11.4%GLM 5
CL-bench LifeNot measured6.3%Only MiniMax M2.5 measured
LMArena Text14461359GLM 5
LMArena Text: instruction following14281353GLM 5
LMArena Text: creative writing14381331GLM 5
LMArena Text: English14581380GLM 5
LMArena Text: non-English14301338GLM 5
LMArena Text: Chinese15111393GLM 5
LMArena Text: German14471361GLM 5
LMArena Text: Japanese14161171GLM 5
LMArena Text: Korean14231233GLM 5
LMArena Text: French14561363GLM 5
LMArena Text: Spanish14541353GLM 5
LMArena Text: Russian14361359GLM 5
LMArena Text: Polish14341334GLM 5
LMArena Text: multi-turn14561364GLM 5
LMArena Text: longer queries14461366GLM 5
LMArena Text: writing and language14371345GLM 5
LMArena Text: entertainment and media14261329GLM 5
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5 and MiniMax M2.5
BenchmarkGLM 5MiniMax M2.5Leader
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
MiniMax M2.5$0.0009Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

GLM 5$0.060Fits in one request
MiniMax M2.5$0.019Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

GLM 5$0.232Exceeds the context window
MiniMax M2.5$0.072Exceeds the context window

MiniMax M2.5 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 MiniMax M2.5
SpecificationZ.ai GLM 5MiniMax M2.5
MakerZ.aiMiniMax
WeightsOpen weightsOpen weights
ReleasedFebruary 11, 2026February 12, 2026
Context window205K205K
Input $/Mtok$1.00$0.30
Output $/Mtok$3.20$1.20
Coding index41.737.2
Independent measurements behind it33
Cost per solved task$0.63$0.62
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5 better than MiniMax M2.5 for coding?

Pick GLM 5 for coding: it scores 41.7 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 2.7x cheaper ($1.20 vs $3.20 per million) and a lower cost per solved task ($0.62 against $0.63).

Which is cheaper, GLM 5 or MiniMax M2.5?

GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GLM 5 costs $0.63 and MiniMax M2.5 $0.62.

Which has the bigger context window, GLM 5 or MiniMax M2.5?

Neither: both take 205K tokens.

How many benchmarks is the GLM 5 vs MiniMax M2.5 comparison based on?

69 benchmarks have a result for both models as of October 22, 2026. GLM 5's coding index rests on 3 independent benchmarks and MiniMax M2.5'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-minimax-minimax-m2-5" title="GLM 5 vs MiniMax M2.5, 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-minimax-minimax-m2-5">LLMBenchmark.ai, GLM 5 vs MiniMax M2.5</a></p>