Enter opens the highlighted result. Esc closes.

GLM 4.7 vs Llama 4 Maverick

GLM 4.7 leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 22.2 to 9.3, and Llama 4 Maverick costs 2.2x less per output token ($1.00 vs $2.20 per million). Updated October 22, 2026; 60 benchmarks have a result for both.

Replace GLM 4.7 Replace Llama 4 Maverick
GLM 4.7Z.ai
Coding
55.1
Overall
56.9
Output $/M
$2.20
57
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
3
vs boards won of 60 shared

GLM 4.7 or Llama 4 Maverick: which to pick

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding.

Pick Llama 4 Maverick for output tokens 2.2x cheaper ($1.00 vs $2.20 per million) and a larger context window (524K against 205K tokens).

Model AGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
60
GLM 4.7 only
21
Llama 4 Maverick only
25
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 4.7 55.1 from 2 benchmarks, Llama 4 Maverick not benchmarked.
Widest category
Agentic work, 78.1 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.7 95.9% against Llama 4 Maverick 17.8%, 78.1 points apart on a 0 to 100 scale.
Output price
GLM 4.7 $2.20 against Llama 4 Maverick $1.00 per million output tokens, 2.2x apart.
Context window
GLM 4.7 takes 205K tokens, Llama 4 Maverick 524K.

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 4.7BarsLlama 4 MaverickTies
Coding70
Intelligence20
Agentic work10
Reasoning70
Math51
Knowledge92
Web design60
General200
All shared boards573
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench VerifiedNot measured21.0%Only Llama 4 Maverick measured
LMArena WebDev1435Not measuredOnly GLM 4.7 measured
AA Coding Index45.316.3GLM 4.7
LiveCodeBench (Vals AI)82.2%47.3%GLM 4.7
SWE-bench Verified (Vals AI)69.4%Not measuredOnly GLM 4.7 measured
LiveCodeBench (Artificial Analysis run)89.4%39.7%GLM 4.7
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)31.8%6.8%GLM 4.7
Terminal-Bench33.4%Not measuredOnly GLM 4.7 measured
WeirdMLNot measured24.5%Only Llama 4 Maverick measured
ALE-Bench399.5173.0GLM 4.7
LMArena Text: coding14541301GLM 4.7
LMArena Text: software and IT14531299GLM 4.7
LMArena WebDev: React1420Not measuredOnly GLM 4.7 measured
LMArena WebDev: HTML1447Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
AA Intelligence Index22.29.3GLM 4.7
Epoch Capabilities Index143.6132.2GLM 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
Design Arena: agents building full-stack apps1050Not measuredOnly GLM 4.7 measured
Design Arena: agents building mobile apps1105Not measuredOnly GLM 4.7 measured
Design Arena: agents building Android apps1112Not measuredOnly GLM 4.7 measured
Design Arena: agents building Godot games1058Not measuredOnly GLM 4.7 measured
τ²-Bench Telecom95.9%17.8%GLM 4.7
Vending-Bench 2$2,377Not measuredOnly GLM 4.7 measured
BrowseComp-Plus64.7%Not measuredOnly 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 index70
Reasoning benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
GPQA Diamond80.0%69.4%GLM 4.7
MMMU Pro (Vals AI)Not measured71.7%Only Llama 4 Maverick measured
GPQA Diamond (Artificial Analysis run)85.9%67.1%GLM 4.7
Humanity's Last Exam (Artificial Analysis run)27.4%4.9%GLM 4.7
GPQA Diamond (Epoch AI run)83.3%Not measuredOnly GLM 4.7 measured
ARC-AGINot measured4.4%Only Llama 4 Maverick measured
ARC-AGI-2Not measured0.0%Only Llama 4 Maverick measured
SimpleBench47.7%27.7%GLM 4.7
Chess puzzles21.0%Not measuredOnly GLM 4.7 measured
LMArena Text: hard prompts14431281GLM 4.7
LMArena Text: expert14241259GLM 4.7
LMArena Text: hard prompts in English14521295GLM 4.7
LMArena Vision: diagramsNot measured1134Only Llama 4 Maverick measured
LMArena Vision: homeworkNot measured1164Only Llama 4 Maverick measured
Kagi LLM BenchmarkNot measured55.9%Only Llama 4 Maverick measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
AIME93.3%25.2%GLM 4.7
MATH 500 (Vals AI)Not measured85.2%Only Llama 4 Maverick measured
MGSM (Vals AI)88.2%92.4%Llama 4 Maverick
AA Math Index95.019.3GLM 4.7
AIME 2025 (Artificial Analysis run)95.0%19.3%GLM 4.7
OTIS Mock AIME83.3%Not measuredOnly GLM 4.7 measured
ProofBench6.0%Not measuredOnly GLM 4.7 measured
LMArena Text: math14241299GLM 4.7
LMArena Text: mathematical work14111295GLM 4.7
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
MMLU Pro82.7%79.4%GLM 4.7
LegalBench (Vals AI)83.4%77.8%GLM 4.7
CaseLaw (Vals AI)54.9%Not measuredOnly GLM 4.7 measured
CorpFin (Vals AI)46.4%49.7%Llama 4 Maverick
TaxEval (Vals AI)68.8%66.6%GLM 4.7
MortgageTax (Vals AI)Not measured58.5%Only Llama 4 Maverick measured
MedQA (Vals AI)93.7%43.3%GLM 4.7
MedCode (Vals AI)32.8%36.5%Llama 4 Maverick
MMLU Pro (Artificial Analysis run)85.6%80.9%GLM 4.7
SimpleQA Verified32.2%Not measuredOnly GLM 4.7 measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science14571288GLM 4.7
LMArena Text: medicine and healthcare14691275GLM 4.7
LMArena Text: legal and government14441286GLM 4.7
LMArena Text: business and finance14291260GLM 4.7
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
Design Arena: websites1225871GLM 4.7
Design Arena: UI components1196896GLM 4.7
Design Arena: game dev1188837GLM 4.7
Design Arena: data viz1195882GLM 4.7
Design Arena: 3D1190900GLM 4.7
Design Arena: all code categories1216879GLM 4.7
Design Arena: SVG1142Not measuredOnly GLM 4.7 measured
Design Arena: ASCII art1165Not measuredOnly 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 index200
General benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
SAGE (Vals AI)Not measured35.7%Only Llama 4 Maverick measured
MedScribe (Vals AI)68.6%54.2%GLM 4.7
IFBench67.9%43.0%GLM 4.7
Long context reasoning (AA-LCR)71.0%50.0%GLM 4.7
DTBenchNot measured61.9%Only Llama 4 Maverick measured
LMCANot measured15.9%Only Llama 4 Maverick measured
Fiction.LiveBenchNot measured46.2%Only Llama 4 Maverick measured
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
CL-bench15.9%Not measuredOnly GLM 4.7 measured
CL-bench Life10.9%Not measuredOnly GLM 4.7 measured
LMArena Text14351287GLM 4.7
LMArena Text: instruction following14121267GLM 4.7
LMArena Text: creative writing14011266GLM 4.7
LMArena VisionNot measured1142Only Llama 4 Maverick measured
LMArena Text: English14531303GLM 4.7
LMArena Text: non-English14171269GLM 4.7
LMArena Text: Chinese14951277GLM 4.7
LMArena Text: German14261291GLM 4.7
LMArena Text: Japanese14391206GLM 4.7
LMArena Text: Korean13991203GLM 4.7
LMArena Text: French14321259GLM 4.7
LMArena Text: Spanish14341293GLM 4.7
LMArena Text: Russian14231286GLM 4.7
LMArena Text: Polish14351275GLM 4.7
LMArena Text: multi-turn14461289GLM 4.7
LMArena Text: longer queries14321280GLM 4.7
LMArena Text: writing and language14111277GLM 4.7
LMArena Text: entertainment and media14001250GLM 4.7
LMArena Vision: EnglishNot measured1150Only Llama 4 Maverick measured
LMArena Vision: ChineseNot measured1141Only Llama 4 Maverick measured
LMArena Vision: reading textNot measured1143Only Llama 4 Maverick measured
LMArena Vision: humorNot measured1100Only Llama 4 Maverick measured
LMArena Vision: creative writingNot measured1099Only Llama 4 Maverick measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.7 and Llama 4 Maverick
BenchmarkGLM 4.7Llama 4 MaverickLeader
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 4.7$0.0017Fits in one request
Llama 4 Maverick$0.0008Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

GLM 4.7$0.037Fits in one request
Llama 4 Maverick$0.021Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

GLM 4.7$0.142Exceeds the context window
Llama 4 Maverick$0.080Fits in one request

Llama 4 Maverick 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 4.7 and Llama 4 Maverick
SpecificationZ.ai GLM 4.7Meta Llama 4 Maverick
MakerZ.aiMeta Llama
WeightsOpen weightsOpen weights
ReleasedDecember 22, 2025April 5, 2025
Context window205K524K
Input $/Mtok$0.60$0.35
Output $/Mtok$2.20$1.00
Coding index55.1Not benchmarked
Independent measurements behind it20
Cost per solved task$0.29$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.7 better than Llama 4 Maverick for coding?

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 2.2x cheaper ($1.00 vs $2.20 per million) and a larger context window (524K against 205K tokens).

Which is cheaper, GLM 4.7 or Llama 4 Maverick?

GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, GLM 4.7 costs $0.29 and Llama 4 Maverick $1.491.

Which has the bigger context window, GLM 4.7 or Llama 4 Maverick?

Llama 4 Maverick, with 524K tokens against 205K.

How many benchmarks is the GLM 4.7 vs Llama 4 Maverick comparison based on?

60 benchmarks have a result for both models as of October 22, 2026. GLM 4.7's coding index rests on 2 independent benchmarks and Llama 4 Maverick's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next