LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GLM 5.3 vs MiniMax M2.7

Updated October 21, 2026. 66 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 5.3 Replace MiniMax M2.7
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
66
MiniMax M2.7MiniMax
Coding
28.4
Overall
22.8
Output $/M
$1.20
0
vs boards won of 66 shared

Decision reading

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 28.4 for MiniMax M2.7.

Pick MiniMax M2.7 when output tokens cost 1.2x less.

Model AGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved taskModel BMiniMax M2.7MiniMax28.4/1001 independent benchmark$0.64 per solved task
Shared results
66
GLM 5.3 only
34
MiniMax M2.7 only
8
Like-for-like categories
8 of 9

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

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 5.3 73.1 from 2 benchmarks, MiniMax M2.7 28.4 from 1 benchmark.
Widest category
Agentic work, 33.0 points apart on average over 5 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GLM 5.3 78.1% against MiniMax M2.7 11.9%, 66.2 points apart on a 0 to 100 scale.
Output price
GLM 5.3 $1.40 against MiniMax M2.7 $1.20 per million output tokens, 1.2x apart.
Context window
GLM 5.3 takes 1.05M tokens, MiniMax M2.7 205K.

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 5.3BarsMiniMax M2.7Ties
Coding150
Intelligence20
Agentic work50
Reasoning60
Math30
Knowledge80
Web design80
General190
All shared boards660
CodingLike-for-likeFour of these boards feed the Vibe Coding Index150
Coding benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
LiveBench coding82.8%Not measuredOnly GLM 5.3 measured
LMArena WebDev16211399GLM 5.3
AA Coding Index74.852.6GLM 5.3
LiveCodeBench (Vals AI)80.5%79.9%GLM 5.3
SWE-bench Verified (Vals AI)95.4%73.8%GLM 5.3
Terminal-Bench 4 (Vals AI)38.9%Not measuredOnly GLM 5.3 measured
Vibe Code Bench (Vals AI)78.1%11.9%GLM 5.3
Code migration (Vals AI)44.2%8.7%GLM 5.3
ProgramBench (Vals AI)1.5%0.0%GLM 5.3
IOI (Vals AI)68.4%Not measuredOnly GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)71.5%48.7%GLM 5.3
Vibe Code Bench 1-100 (Vals AI)20.0%Not measuredOnly GLM 5.3 measured
SkillsBench (Vals AI)47.5%Not measuredOnly GLM 5.3 measured
CyberBench (Vals AI)72.1%Not measuredOnly GLM 5.3 measured
SciCode59.0%50.1%GLM 5.3
Terminal-Bench Hard (Artificial Analysis run)Not measured39.4%Only MiniMax M2.7 measured
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
FrontierCode40.1%Not measuredOnly GLM 5.3 measured
FrontierSWE30.2%Not measuredOnly GLM 5.3 measured
WeirdML75.4%37.0%GLM 5.3
ALE-Bench1317.4599.3GLM 5.3
LMArena Text: coding14971454GLM 5.3
LMArena Text: software and IT14931446GLM 5.3
LMArena WebDev: React16411388GLM 5.3
LMArena WebDev: HTML15951401GLM 5.3
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
AA Intelligence Index44.822.8GLM 5.3
Epoch Capabilities Index156.0145.8GLM 5.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
AA Agentic Index53.115.3GLM 5.3
Design Arena: agents building mobile apps1194Not measuredOnly GLM 5.3 measured
Design Arena: HTML slides1189Not measuredOnly GLM 5.3 measured
Design Arena: PowerPoint slides1255Not measuredOnly GLM 5.3 measured
LiveBench research73.2%Not measuredOnly GLM 5.3 measured
LiveBench browser0.0%Not measuredOnly GLM 5.3 measured
LiveBench long agentic35.9%Not measuredOnly GLM 5.3 measured
SREBench (Vals AI)9.2%Not measuredOnly GLM 5.3 measured
Finance Agent (Vals AI)55.8%27.9%GLM 5.3
Tax Agent Bench (Vals AI)39.7%6.9%GLM 5.3
Legal Research Bench (Vals AI)49.0%10.6%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)14.6%Not measuredOnly GLM 5.3 measured
Excel Modeling Benchmark (Vals AI)56.3%28.4%GLM 5.3
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly GLM 5.3 measured
τ²-Bench TelecomNot measured84.8%Only MiniMax M2.7 measured
APEX-Agents56.6%Not measuredOnly GLM 5.3 measured
Vending-Bench 2$8,164Not measuredOnly GLM 5.3 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
GPQA Diamond88.1%86.6%GLM 5.3
LiveBench reasoning85.8%Not measuredOnly GLM 5.3 measured
MysteryMechanism (Vals AI)23.0%Not measuredOnly GLM 5.3 measured
GPQA Diamond (Artificial Analysis run)91.7%87.4%GLM 5.3
Humanity's Last Exam (Artificial Analysis run)42.3%29.6%GLM 5.3
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly GLM 5.3 measured
Chess puzzles37.0%Not measuredOnly GLM 5.3 measured
Mystery game puzzles33.0%Not measuredOnly GLM 5.3 measured
LMArena Text: hard prompts14901422GLM 5.3
LMArena Text: expert15141443GLM 5.3
LMArena Text: hard prompts in English14961441GLM 5.3
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
AIMENot measured91.0%Only MiniMax M2.7 measured
OTIS Mock AIME91.1%Not measuredOnly GLM 5.3 measured
FrontierMath, tiers 1 to 368.8%Not measuredOnly GLM 5.3 measured
FrontierMath, tier 429.3%Not measuredOnly GLM 5.3 measured
ProofBench49.0%3.0%GLM 5.3
LMArena Text: math14951421GLM 5.3
LMArena Text: mathematical work14971437GLM 5.3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
Knowledge benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
MMLU Pro86.8%80.4%GLM 5.3
LegalBench (Vals AI)84.8%84.0%GLM 5.3
CaseLaw (Vals AI)Not measured60.9%Only MiniMax M2.7 measured
CorpFin (Vals AI)Not measured61.2%Only MiniMax M2.7 measured
TaxEval (Vals AI)72.4%66.6%GLM 5.3
MedCode (Vals AI)42.9%34.4%GLM 5.3
SimpleQA Verified41.0%Not measuredOnly GLM 5.3 measured
LMArena Text: science14981416GLM 5.3
LMArena Text: medicine and healthcare14811409GLM 5.3
LMArena Text: legal and government14731403GLM 5.3
LMArena Text: business and finance14591407GLM 5.3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
Design Arena: websites12951243GLM 5.3
Design Arena: UI components13141210GLM 5.3
Design Arena: game dev13111210GLM 5.3
Design Arena: data viz12601233GLM 5.3
Design Arena: 3D13321195GLM 5.3
Design Arena: all code categories13041233GLM 5.3
Design Arena: SVG12921136GLM 5.3
Design Arena: ASCII art12131136GLM 5.3
LiveBench design77.3%Not measuredOnly GLM 5.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
Vals Index59.7%Not measuredOnly GLM 5.3 measured
LiveBench data analysis70.2%Not measuredOnly GLM 5.3 measured
Public Benefits Bench (Vals AI)68.5%Not measuredOnly GLM 5.3 measured
MedScribe (Vals AI)88.8%79.9%GLM 5.3
IFBenchNot measured75.7%Only MiniMax M2.7 measured
Long context reasoning (AA-LCR)79.7%78.3%GLM 5.3
DTBench87.7%Not measuredOnly GLM 5.3 measured
LMCA55.5%Not measuredOnly GLM 5.3 measured
ExploitBenchNot measured13.3%Only MiniMax M2.7 measured
LMArena Text14741405GLM 5.3
LMArena Text: instruction following14791405GLM 5.3
LMArena Text: creative writing14581354GLM 5.3
LMArena Text: English14821426GLM 5.3
LMArena Text: non-English14591382GLM 5.3
LMArena Text: Chinese15321442GLM 5.3
LMArena Text: German14881398GLM 5.3
LMArena Text: Japanese14601260GLM 5.3
LMArena Text: Korean14601314GLM 5.3
LMArena Text: French15031424GLM 5.3
LMArena Text: Spanish14621402GLM 5.3
LMArena Text: Russian14691383GLM 5.3
LMArena Text: Polish14661387GLM 5.3
LMArena Text: multi-turn14721412GLM 5.3
LMArena Text: longer queries14831418GLM 5.3
LMArena Text: writing and language14691376GLM 5.3
LMArena Text: entertainment and media14471360GLM 5.3
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5.3 and MiniMax M2.7
BenchmarkGLM 5.3MiniMax M2.7Leader
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 5.3$0.0008Fits in one request
MiniMax M2.7$0.0009Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

GLM 5.3$0.0081Fits in one request
MiniMax M2.7$0.019Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

GLM 5.3$0.030Fits in one request
MiniMax M2.7$0.072Exceeds the context window

GLM 5.3 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 5.3 and MiniMax M2.7
SpecificationZ.ai GLM 5.3MiniMax M2.7
MakerZ.aiMiniMax
WeightsOpen weightsOpen weights
ReleasedAugust 18, 2026March 18, 2026
Context window1.05M205K
Input $/Mtok$0.079$0.30
Output $/Mtok$1.40$1.20
Coding index73.128.4
Independent measurements behind it21
Cost per solved task$0.36$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.3 better than MiniMax M2.7 for coding?

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 28.4 for MiniMax M2.7. Pick MiniMax M2.7 when output tokens cost 1.2x less.

Which is cheaper, GLM 5.3 or MiniMax M2.7?

GLM 5.3 costs $0.079 per million input tokens and $1.40 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GLM 5.3 costs $0.36 and MiniMax M2.7 $0.64.

Which has the bigger context window, GLM 5.3 or MiniMax M2.7?

GLM 5.3, with 1.05M tokens against 205K.

How many benchmarks is the GLM 5.3 vs MiniMax M2.7 comparison based on?

66 benchmarks have a result for both models as of October 21, 2026. GLM 5.3's coding index rests on 2 independent benchmarks and MiniMax M2.7's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next