LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GLM 4.6 vs GLM 4.7

Updated October 21, 2026. 64 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 4.6 Replace GLM 4.7
GLM 4.6Z.ai
Coding
52.2
Overall
18.5
Output $/M
$2.20
20
GLM 4.7Z.ai
Coding
33.6
Overall
22.2
Output $/M
$1.98
44
vs boards won of 64 shared

Decision reading

Pick GLM 4.6 for coding: it scores 52.2 on the Vibe Coding Index against 33.6 for GLM 4.7.

Pick GLM 4.7 when output tokens cost 1.1x less, or when what matters is LMArena WebDev or LiveCodeBench (Vals AI), where it leads.

Model AGLM 4.6Z.ai52.2/1002 independent benchmarksNo cost per solved taskModel BGLM 4.7Z.ai33.6/1001 independent benchmark$0.29 per solved task
Shared results
64
GLM 4.6 only
2
GLM 4.7 only
16
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 4.6 52.2 from 2 benchmarks, GLM 4.7 33.6 from 1 benchmark.
Widest category
Agentic work, 8.3 points apart on average over 5 shared benchmarks.
Widest single gap
IFBench: GLM 4.6 43.4% against GLM 4.7 67.9%, 24.5 points apart on a 0 to 100 scale.
Output price
GLM 4.6 $2.20 against GLM 4.7 $1.98 per million output tokens, 1.1x 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 4.6BarsGLM 4.7Ties
Coding28
Intelligence01
Agentic work14
Reasoning15
Math33
Knowledge28
Web design07
General118
All shared boards2044
CodingLike-for-likeFour of these boards feed the Vibe Coding Index28
Coding benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
SWE-bench Verified68.2%Not measuredOnly GLM 4.6 measured
LMArena WebDev13411435GLM 4.7
AA Coding Index45.845.3GLM 4.6
LiveCodeBench (Vals AI)81.0%82.2%GLM 4.7
SWE-bench Verified (Vals AI)Not measured69.4%Only GLM 4.7 measured
Vibe Code Bench (Vals AI)3.1%Not measuredOnly GLM 4.6 measured
LiveCodeBench (Artificial Analysis run)69.5%89.4%GLM 4.7
Terminal-Bench Hard (Artificial Analysis run)28.8%31.8%GLM 4.7
Terminal-Bench24.5%33.4%GLM 4.7
ALE-Bench340.8399.5GLM 4.7
LMArena Text: coding14491454GLM 4.7
LMArena Text: software and IT14551453GLM 4.6
LMArena WebDev: ReactNot measured1420Only GLM 4.7 measured
LMArena WebDev: HTML13501447GLM 4.7
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
AA Intelligence Index18.522.2GLM 4.7
Epoch Capabilities IndexNot measured143.6Only GLM 4.7 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
Design Arena: agents building full-stack apps10291050GLM 4.7
Design Arena: agents building mobile apps10961105GLM 4.7
Design Arena: agents building Android apps10901118GLM 4.7
Design Arena: agents building Godot games11801058GLM 4.6
τ²-Bench Telecom76.9%95.9%GLM 4.7
Vending-Bench 2Not measured$2,377Only GLM 4.7 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
GPQA Diamond74.5%80.0%GLM 4.7
GPQA Diamond (Artificial Analysis run)78.0%85.9%GLM 4.7
Humanity's Last Exam (Artificial Analysis run)14.5%27.4%GLM 4.7
GPQA Diamond (Epoch AI run)Not measured83.3%Only GLM 4.7 measured
SimpleBenchNot measured47.7%Only GLM 4.7 measured
Chess puzzlesNot measured21.0%Only GLM 4.7 measured
LMArena Text: hard prompts14401443GLM 4.7
LMArena Text: expert14321424GLM 4.6
LMArena Text: hard prompts in English14451452GLM 4.7
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
AIME92.7%93.3%GLM 4.7
MGSM (Vals AI)89.8%88.2%GLM 4.6
AA Math Index86.095.0GLM 4.7
AIME 2025 (Artificial Analysis run)86.0%95.0%GLM 4.7
OTIS Mock AIMENot measured83.3%Only GLM 4.7 measured
ProofBenchNot measured6.0%Only GLM 4.7 measured
LMArena Text: math14321424GLM 4.6
LMArena Text: mathematical work14471411GLM 4.6
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28
Knowledge benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
MMLU Pro82.2%82.7%GLM 4.7
LegalBench (Vals AI)79.6%83.4%GLM 4.7
CaseLaw (Vals AI)Not measured54.9%Only GLM 4.7 measured
CorpFin (Vals AI)56.8%46.4%GLM 4.6
TaxEval (Vals AI)66.2%68.8%GLM 4.7
MedQA (Vals AI)92.2%93.7%GLM 4.7
MedCode (Vals AI)Not measured32.8%Only GLM 4.7 measured
MMLU Pro (Artificial Analysis run)82.9%85.6%GLM 4.7
SimpleQA VerifiedNot measured32.2%Only GLM 4.7 measured
LMArena Text: science14561457GLM 4.7
LMArena Text: medicine and healthcare14551469GLM 4.7
LMArena Text: legal and government14481444GLM 4.6
LMArena Text: business and finance14161429GLM 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 index07
Web design benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
Design Arena: websites11741226GLM 4.7
Design Arena: UI components11471199GLM 4.7
Design Arena: game dev11511189GLM 4.7
Design Arena: data viz11611195GLM 4.7
Design Arena: 3D11291191GLM 4.7
Design Arena: all code categories11661217GLM 4.7
Design Arena: SVG11081142GLM 4.7
Design Arena: ASCII artNot measured1165Only GLM 4.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index118
General benchmarks for GLM 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
MedScribe (Vals AI)Not measured68.6%Only GLM 4.7 measured
IFBench43.4%67.9%GLM 4.7
Long context reasoning (AA-LCR)54.0%71.0%GLM 4.7
CL-benchNot measured15.9%Only GLM 4.7 measured
CL-bench LifeNot measured10.9%Only GLM 4.7 measured
LMArena Text14401435GLM 4.6
LMArena Text: instruction following14101412GLM 4.7
LMArena Text: creative writing14121401GLM 4.6
LMArena Text: English14491453GLM 4.7
LMArena Text: non-English14261417GLM 4.6
LMArena Text: Chinese14991495GLM 4.6
LMArena Text: German14471426GLM 4.6
LMArena Text: Japanese13931439GLM 4.7
LMArena Text: Korean14001399GLM 4.6
LMArena Text: French14591432GLM 4.6
LMArena Text: Spanish14361434GLM 4.6
LMArena Text: Russian14181423GLM 4.7
LMArena Text: Polish14471435GLM 4.6
LMArena Text: multi-turn14271446GLM 4.7
LMArena Text: longer queries14221432GLM 4.7
LMArena Text: writing and language14151411GLM 4.6
LMArena Text: entertainment and media14091400GLM 4.6
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 4.6 and GLM 4.7
BenchmarkGLM 4.6GLM 4.7Leader
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 4.6$0.0016Fits in one request
GLM 4.7$0.0015Fits in one request

GLM 4.7 costs less

Repository review

50K input + 3K output tokens

GLM 4.6$0.034Fits in one request
GLM 4.7$0.033Fits in one request

GLM 4.7 costs less

Agent loop

200K input + 10K output tokens

GLM 4.6$0.132Exceeds the context window
GLM 4.7$0.128Exceeds the context window

GLM 4.7 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 4.6 and GLM 4.7
SpecificationZ.ai GLM 4.6Z.ai GLM 4.7
MakerZ.aiZ.ai
WeightsOpen weightsOpen weights
ReleasedSeptember 30, 2025December 22, 2025
Context window205K205K
Input $/Mtok$0.55$0.54
Output $/Mtok$2.20$1.98
Coding index52.233.6
Independent measurements behind it21
Cost per solved taskNot computable$0.29
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.6 better than GLM 4.7 for coding?

Pick GLM 4.6 for coding: it scores 52.2 on the Vibe Coding Index against 33.6 for GLM 4.7. Pick GLM 4.7 when output tokens cost 1.1x less, or when what matters is LMArena WebDev or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, GLM 4.6 or GLM 4.7?

GLM 4.6 costs $0.55 per million input tokens and $2.20 per million output tokens; GLM 4.7 costs $0.54 and $1.98. Cost per solved task is known for GLM 4.7 only.

Which has the bigger context window, GLM 4.6 or GLM 4.7?

Neither: both take 205K tokens.

How many benchmarks is the GLM 4.6 vs GLM 4.7 comparison based on?

64 benchmarks have a result for both models as of October 21, 2026. GLM 4.6's coding index rests on 2 independent benchmarks and GLM 4.7's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next