Enter opens the highlighted result. Esc closes.

GLM 4.6V vs GLM 5.1

GLM 5.1 leads GLM 4.6V on the Artificial Analysis Intelligence Index, 26.1 to 11.2, and GLM 4.6V costs 4.9x less per output token ($0.90 vs $4.40 per million). Updated October 21, 2026; 27 benchmarks have a result for both.

Replace GLM 4.6V Replace GLM 5.1
GLM 4.6VZ.ai
Coding
No data
Overall
11.2
Output $/M
$0.90
0
GLM 5.1Z.ai
Coding
49.2
Overall
26.1
Output $/M
$4.40
27
vs boards won of 27 shared

GLM 4.6V or GLM 5.1: which to pick

Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; GLM 4.6V has none, so the two cannot be ranked on coding.

Pick GLM 4.6V for output tokens 4.9x cheaper ($0.90 vs $4.40 per million).

Model AGLM 4.6VZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 5.1Z.ai49.2/1003 independent benchmarks$0.60 per solved task
Shared results
27
GLM 4.6V only
11
GLM 5.1 only
62
Like-for-like categories
6 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 4.6V not benchmarked, GLM 5.1 49.2 from 3 benchmarks.
Widest category
Agentic work, 66.1 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.6V 31.6% against GLM 5.1 97.7%, 66.1 points apart on a 0 to 100 scale.
Output price
GLM 4.6V $0.90 against GLM 5.1 $4.40 per million output tokens, 4.9x apart.
Context window
GLM 4.6V takes 131K tokens, GLM 5.1 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 4.6VBarsGLM 5.1Ties
Coding03
Intelligence01
Agentic work01
Reasoning05
Knowledge04
General013
All shared boards027
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
LMArena WebDevNot measured1508Only GLM 5.1 measured
AA Coding IndexNot measured55.8Only GLM 5.1 measured
LiveCodeBench (Vals AI)Not measured81.4%Only GLM 5.1 measured
SWE-bench Verified (Vals AI)Not measured76.4%Only GLM 5.1 measured
Vibe Code Bench (Vals AI)Not measured31.5%Only GLM 5.1 measured
Code migration (Vals AI)Not measured25.8%Only GLM 5.1 measured
ProgramBench (Vals AI)Not measured0.0%Only GLM 5.1 measured
Terminal-Bench 2.1 (Vals AI)Not measured56.9%Only GLM 5.1 measured
LiveCodeBench (Artificial Analysis run)41.1%Not measuredOnly GLM 4.6V measured
SciCodeNot measured44.8%Only GLM 5.1 measured
Terminal-Bench Hard (Artificial Analysis run)14.4%43.2%GLM 5.1
WeirdMLNot measured57.1%Only GLM 5.1 measured
ALE-BenchNot measured887.1Only GLM 5.1 measured
LMArena Text: coding13891485GLM 5.1
LMArena Text: software and IT13911484GLM 5.1
LMArena WebDev: ReactNot measured1505Only GLM 5.1 measured
LMArena WebDev: HTMLNot measured1508Only GLM 5.1 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
AA Intelligence Index11.226.1GLM 5.1
Epoch Capabilities IndexNot measured149.8Only GLM 5.1 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
AA Agentic IndexNot measured23.9Only GLM 5.1 measured
Design Arena: agents building web appsNot measured1175Only GLM 5.1 measured
Design Arena: agents building full-stack appsNot measured1167Only GLM 5.1 measured
Design Arena: agents building mobile appsNot measured1162Only GLM 5.1 measured
Design Arena: agents building Android appsNot measured1180Only GLM 5.1 measured
Design Arena: agents building Godot gamesNot measured1053Only GLM 5.1 measured
Design Arena: agents building gamesNot measured1164Only GLM 5.1 measured
Design Arena: HTML slidesNot measured1170Only GLM 5.1 measured
Design Arena: PowerPoint slidesNot measured1188Only GLM 5.1 measured
Design Arena: spreadsheetsNot measured1315Only GLM 5.1 measured
Finance Agent (Vals AI)Not measured44.8%Only GLM 5.1 measured
Legal Research Bench (Vals AI)Not measured27.9%Only GLM 5.1 measured
τ²-Bench Telecom31.6%97.7%GLM 5.1
APEX-AgentsNot measured40.9%Only GLM 5.1 measured
Vending-Bench 2Not measured$5,634Only GLM 5.1 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
GPQA DiamondNot measured84.5%Only GLM 5.1 measured
GPQA Diamond (Artificial Analysis run)71.9%86.8%GLM 5.1
Humanity's Last Exam (Artificial Analysis run)9.6%30.1%GLM 5.1
GPQA Diamond (Epoch AI run)Not measured89.9%Only GLM 5.1 measured
SimpleBenchNot measured55.1%Only GLM 5.1 measured
Chess puzzlesNot measured20.0%Only GLM 5.1 measured
LMArena Text: hard prompts13671473GLM 5.1
LMArena Text: expert13711478GLM 5.1
LMArena Text: hard prompts in English13911482GLM 5.1
LMArena Vision: diagrams1182Not measuredOnly GLM 4.6V measured
LMArena Vision: homework1155Not measuredOnly GLM 4.6V measured
Neither model has a result on the other 10 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
AIMENot measured91.9%Only GLM 5.1 measured
AA Math Index85.3Not measuredOnly GLM 4.6V measured
AIME 2025 (Artificial Analysis run)85.3%Not measuredOnly GLM 4.6V measured
OTIS Mock AIMENot measured93.3%Only GLM 5.1 measured
FrontierMath, tiers 1 to 3Not measured36.8%Only GLM 5.1 measured
ProofBenchNot measured22.2%Only GLM 5.1 measured
LMArena Text: mathNot measured1473Only GLM 5.1 measured
LMArena Text: mathematical workNot measured1470Only GLM 5.1 measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
MMLU ProNot measured86.9%Only GLM 5.1 measured
LegalBench (Vals AI)Not measured84.4%Only GLM 5.1 measured
CaseLaw (Vals AI)Not measured51.5%Only GLM 5.1 measured
CorpFin (Vals AI)Not measured64.5%Only GLM 5.1 measured
TaxEval (Vals AI)Not measured71.2%Only GLM 5.1 measured
MedCode (Vals AI)Not measured41.6%Only GLM 5.1 measured
MMLU Pro (Artificial Analysis run)79.9%Not measuredOnly GLM 4.6V measured
SimpleQA VerifiedNot measured34.0%Only GLM 5.1 measured
LMArena Text: science13891478GLM 5.1
LMArena Text: medicine and healthcare13891474GLM 5.1
LMArena Text: legal and government13931465GLM 5.1
LMArena Text: business and finance13591452GLM 5.1
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
Design Arena: websitesNot measured1290Only GLM 5.1 measured
Design Arena: UI componentsNot measured1292Only GLM 5.1 measured
Design Arena: game devNot measured1265Only GLM 5.1 measured
Design Arena: data vizNot measured1366Only GLM 5.1 measured
Design Arena: 3DNot measured1336Only GLM 5.1 measured
Design Arena: all code categoriesNot measured1268Only GLM 5.1 measured
Design Arena: SVGNot measured1218Only GLM 5.1 measured
Design Arena: ASCII artNot measured1142Only GLM 5.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
General benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
Public Benefits Bench (Vals AI)Not measured61.8%Only GLM 5.1 measured
MedScribe (Vals AI)Not measured72.3%Only GLM 5.1 measured
IFBench30.1%76.3%GLM 5.1
Long context reasoning (AA-LCR)48.7%73.7%GLM 5.1
ExploitBenchNot measured18.1%Only GLM 5.1 measured
LMArena Text13761463GLM 5.1
LMArena Text: instruction following13501453GLM 5.1
LMArena Text: creative writing13471453GLM 5.1
LMArena Vision1164Not measuredOnly GLM 4.6V measured
LMArena Text: English13951476GLM 5.1
LMArena Text: non-English13581448GLM 5.1
LMArena Text: Chinese14251515GLM 5.1
LMArena Text: GermanNot measured1467Only GLM 5.1 measured
LMArena Text: JapaneseNot measured1435Only GLM 5.1 measured
LMArena Text: KoreanNot measured1424Only GLM 5.1 measured
LMArena Text: FrenchNot measured1470Only GLM 5.1 measured
LMArena Text: SpanishNot measured1468Only GLM 5.1 measured
LMArena Text: Russian13391454GLM 5.1
LMArena Text: PolishNot measured1449Only GLM 5.1 measured
LMArena Text: multi-turn13591473GLM 5.1
LMArena Text: longer queries13571467GLM 5.1
LMArena Text: writing and language13471454GLM 5.1
LMArena Text: entertainment and media13431442GLM 5.1
LMArena Vision: English1179Not measuredOnly GLM 4.6V measured
LMArena Vision: Chinese1217Not measuredOnly GLM 4.6V measured
LMArena Vision: reading text1171Not measuredOnly GLM 4.6V measured
LMArena Vision: creative writing1113Not measuredOnly GLM 4.6V measured
Neither model has a result on the other 19 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.6V and GLM 5.1
BenchmarkGLM 4.6VGLM 5.1Leader
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 4.6V$0.0008Fits in one request
GLM 5.1$0.0036Fits in one request

GLM 4.6V costs less

Repository review

50K input + 3K output tokens

GLM 4.6V$0.018Fits in one request
GLM 5.1$0.083Fits in one request

GLM 4.6V costs less

Agent loop

200K input + 10K output tokens

GLM 4.6V$0.069Exceeds the context window
GLM 5.1$0.324Exceeds the context window

GLM 4.6V 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 4.6V and GLM 5.1
SpecificationZ.ai GLM 4.6VZ.ai GLM 5.1
MakerZ.aiZ.ai
WeightsOpen weightsOpen weights
ReleasedDecember 8, 2025April 7, 2026
Context window131K205K
Input $/Mtok$0.30$1.40
Output $/Mtok$0.90$4.40
Coding indexNot benchmarked49.2
Independent measurements behind it03
Cost per solved taskNot computable$0.60
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.6V better than GLM 5.1 for coding?

Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; GLM 4.6V has none, so the two cannot be ranked on coding. Pick GLM 4.6V for output tokens 4.9x cheaper ($0.90 vs $4.40 per million).

Which is cheaper, GLM 4.6V or GLM 5.1?

GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens; GLM 5.1 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.1 only.

Which has the bigger context window, GLM 4.6V or GLM 5.1?

GLM 5.1, with 205K tokens against 131K.

How many benchmarks is the GLM 4.6V vs GLM 5.1 comparison based on?

27 benchmarks have a result for both models as of October 21, 2026. GLM 4.6V's coding index rests on 0 independent benchmarks and GLM 5.1's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next