LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GLM 5.1 vs MiniMax M2.7

Updated October 21, 2026. 71 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 5.1 Replace MiniMax M2.7
GLM 5.1Z.ai
Coding
44.0
Overall
26.1
Output $/M
$4.40
64
MiniMax M2.7MiniMax
Coding
28.4
Overall
22.8
Output $/M
$1.20
6
vs boards won of 71 shared, 1 tied

Decision reading

Pick GLM 5.1 for coding: it scores 44.0 on the Vibe Coding Index against 28.4 for MiniMax M2.7.

Pick MiniMax M2.7 when output tokens cost 3.7x less, or when what matters is SciCode or GPQA Diamond, where it leads.

Model AGLM 5.1Z.ai44.0/1001 independent benchmark$0.60 per solved taskModel BMiniMax M2.7MiniMax28.4/1001 independent benchmark$0.64 per solved task
Shared results
71
GLM 5.1 only
18
MiniMax M2.7 only
3
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 5.1 44.0 from 1 benchmark, MiniMax M2.7 28.4 from 1 benchmark.
Widest category
Agentic work, 13.9 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: Japanese: GLM 5.1 1435 against MiniMax M2.7 1260, 29.1 points apart on a 0 to 100 scale.
Output price
GLM 5.1 $4.40 against MiniMax M2.7 $1.20 per million output tokens, 3.7x 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 5.1BarsMiniMax M2.7Ties
Coding1411 tie
Intelligence20
Agentic work40
Reasoning42
Math40
Knowledge91
Web design80
General192
All shared boards6461 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index141
Coding benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
LMArena WebDev15081399GLM 5.1
AA Coding Index55.852.6GLM 5.1
LiveCodeBench (Vals AI)81.4%79.9%GLM 5.1
SWE-bench Verified (Vals AI)76.4%73.8%GLM 5.1
Vibe Code Bench (Vals AI)31.5%11.9%GLM 5.1
Code migration (Vals AI)25.8%8.7%GLM 5.1
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)56.9%48.7%GLM 5.1
SciCode44.8%50.1%MiniMax M2.7
Terminal-Bench Hard (Artificial Analysis run)43.2%39.4%GLM 5.1
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
WeirdML57.1%37.0%GLM 5.1
ALE-Bench887.1599.3GLM 5.1
LMArena Text: coding14851454GLM 5.1
LMArena Text: software and IT14841446GLM 5.1
LMArena WebDev: React15051388GLM 5.1
LMArena WebDev: HTML15081401GLM 5.1
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
AA Intelligence Index26.122.8GLM 5.1
Epoch Capabilities Index149.8145.8GLM 5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
Agentic work benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
AA Agentic Index23.915.3GLM 5.1
Design Arena: agents building web apps1175Not measuredOnly GLM 5.1 measured
Design Arena: agents building full-stack apps1167Not measuredOnly GLM 5.1 measured
Design Arena: agents building mobile apps1162Not measuredOnly GLM 5.1 measured
Design Arena: agents building Android apps1186Not measuredOnly GLM 5.1 measured
Design Arena: agents building Godot games1053Not measuredOnly GLM 5.1 measured
Design Arena: agents building games1164Not measuredOnly GLM 5.1 measured
Design Arena: HTML slides1170Not measuredOnly GLM 5.1 measured
Design Arena: PowerPoint slides1189Not measuredOnly GLM 5.1 measured
Design Arena: spreadsheets1315Not measuredOnly GLM 5.1 measured
Finance Agent (Vals AI)44.8%27.9%GLM 5.1
Tax Agent Bench (Vals AI)Not measured6.9%Only MiniMax M2.7 measured
Legal Research Bench (Vals AI)27.9%10.6%GLM 5.1
Excel Modeling Benchmark (Vals AI)Not measured28.4%Only MiniMax M2.7 measured
τ²-Bench Telecom97.7%84.8%GLM 5.1
APEX-Agents40.9%Not measuredOnly GLM 5.1 measured
Vending-Bench 2$5,634Not measuredOnly GLM 5.1 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
GPQA Diamond84.5%86.6%MiniMax M2.7
GPQA Diamond (Artificial Analysis run)86.8%87.4%MiniMax M2.7
Humanity's Last Exam (Artificial Analysis run)30.1%29.6%GLM 5.1
GPQA Diamond (Epoch AI run)89.9%Not measuredOnly GLM 5.1 measured
SimpleBench55.1%Not measuredOnly GLM 5.1 measured
Chess puzzles20.0%Not measuredOnly GLM 5.1 measured
LMArena Text: hard prompts14731422GLM 5.1
LMArena Text: expert14781443GLM 5.1
LMArena Text: hard prompts in English14821441GLM 5.1
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
AIME91.9%91.0%GLM 5.1
OTIS Mock AIME93.3%Not measuredOnly GLM 5.1 measured
FrontierMath, tiers 1 to 336.8%Not measuredOnly GLM 5.1 measured
ProofBench22.2%3.0%GLM 5.1
LMArena Text: math14731421GLM 5.1
LMArena Text: mathematical work14701437GLM 5.1
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
Knowledge benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
MMLU Pro86.9%80.4%GLM 5.1
LegalBench (Vals AI)84.4%84.0%GLM 5.1
CaseLaw (Vals AI)51.5%60.9%MiniMax M2.7
CorpFin (Vals AI)64.5%61.2%GLM 5.1
TaxEval (Vals AI)71.2%66.6%GLM 5.1
MedCode (Vals AI)41.6%34.4%GLM 5.1
SimpleQA Verified34.0%Not measuredOnly GLM 5.1 measured
LMArena Text: science14781416GLM 5.1
LMArena Text: medicine and healthcare14741409GLM 5.1
LMArena Text: legal and government14651403GLM 5.1
LMArena Text: business and finance14521407GLM 5.1
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 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
Design Arena: websites12901243GLM 5.1
Design Arena: UI components12921210GLM 5.1
Design Arena: game dev12651210GLM 5.1
Design Arena: data viz13661233GLM 5.1
Design Arena: 3D13361195GLM 5.1
Design Arena: all code categories12681233GLM 5.1
Design Arena: SVG12171136GLM 5.1
Design Arena: ASCII art11421136GLM 5.1
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index192
General benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax M2.7Leader
Public Benefits Bench (Vals AI)61.8%Not measuredOnly GLM 5.1 measured
MedScribe (Vals AI)72.3%79.9%MiniMax M2.7
IFBench76.3%75.7%GLM 5.1
Long context reasoning (AA-LCR)73.7%78.3%MiniMax M2.7
ExploitBench18.1%13.3%GLM 5.1
LMArena Text14631405GLM 5.1
LMArena Text: instruction following14531405GLM 5.1
LMArena Text: creative writing14531354GLM 5.1
LMArena Text: English14761426GLM 5.1
LMArena Text: non-English14481382GLM 5.1
LMArena Text: Chinese15151442GLM 5.1
LMArena Text: German14671398GLM 5.1
LMArena Text: Japanese14351260GLM 5.1
LMArena Text: Korean14241314GLM 5.1
LMArena Text: French14701424GLM 5.1
LMArena Text: Spanish14681402GLM 5.1
LMArena Text: Russian14541383GLM 5.1
LMArena Text: Polish14491387GLM 5.1
LMArena Text: multi-turn14731412GLM 5.1
LMArena Text: longer queries14671418GLM 5.1
LMArena Text: writing and language14541376GLM 5.1
LMArena Text: entertainment and media14421360GLM 5.1
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5.1 and MiniMax M2.7
BenchmarkGLM 5.1MiniMax 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 5.1$0.0036Fits in one request
MiniMax M2.7$0.0009Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

GLM 5.1$0.083Fits in one request
MiniMax M2.7$0.019Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

GLM 5.1$0.324Exceeds the context window
MiniMax M2.7$0.072Exceeds the context window

MiniMax M2.7 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 5.1 and MiniMax M2.7
SpecificationZ.ai GLM 5.1MiniMax M2.7
MakerZ.aiMiniMax
WeightsOpen weightsOpen weights
ReleasedApril 7, 2026March 18, 2026
Context window205K205K
Input $/Mtok$1.40$0.30
Output $/Mtok$4.40$1.20
Coding index44.028.4
Independent measurements behind it11
Cost per solved task$0.60$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.1 better than MiniMax M2.7 for coding?

Pick GLM 5.1 for coding: it scores 44.0 on the Vibe Coding Index against 28.4 for MiniMax M2.7. Pick MiniMax M2.7 when output tokens cost 3.7x less, or when what matters is SciCode or GPQA Diamond, where it leads.

Which is cheaper, GLM 5.1 or MiniMax M2.7?

GLM 5.1 costs $1.40 per million input tokens and $4.40 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GLM 5.1 costs $0.60 and MiniMax M2.7 $0.64.

Which has the bigger context window, GLM 5.1 or MiniMax M2.7?

Neither: both take 205K tokens.

How many benchmarks is the GLM 5.1 vs MiniMax M2.7 comparison based on?

71 benchmarks have a result for both models as of October 21, 2026. GLM 5.1's coding index rests on 1 independent benchmark 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