Enter opens the highlighted result. Esc closes.

GLM 5.2 vs Grok 4.20

Updated October 21, 2026. 43 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 5.2 Replace Grok 4.20
GLM 5.2Z.ai
Coding
61.1
Overall
33.7
Output $/M
$4.40
34
Grok 4.20xAI
Coding
33.3
Overall
25.7
Output $/M
$2.50
9
vs boards won of 43 shared

Decision reading

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 33.3 for Grok 4.20.

Pick Grok 4.20 when output tokens cost 1.8x less, or when a solved task costs $0.72 against $0.86.

Model AGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved taskModel BGrok 4.20xAI33.3/1002 independent benchmarks$0.72 per solved task
Shared results
43
GLM 5.2 only
54
Grok 4.20 only
11
Like-for-like categories
7 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 5.2 61.1 from 4 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
Widest category
Coding, 25.3 points apart on average over 7 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GLM 5.2 64.0% against Grok 4.20 4.1%, 59.9 points apart on a 0 to 100 scale.
Output price
GLM 5.2 $4.40 against Grok 4.20 $2.50 per million output tokens, 1.8x apart.
Context window
GLM 5.2 takes 1.05M tokens, Grok 4.20 2M.

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 5.2BarsGrok 4.20Ties
Coding61
Intelligence11
Agentic work101
Reasoning14
Knowledge41
Web design80
General41
All shared boards349
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
Coding benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
LMArena WebDev1604Not measuredOnly GLM 5.2 measured
AA Coding Index68.8Not measuredOnly GLM 5.2 measured
LiveCodeBench (Vals AI)69.5%84.3%Grok 4.20
SWE-bench Verified (Vals AI)82.8%72.2%GLM 5.2
Vibe Code Bench (Vals AI)64.0%4.1%GLM 5.2
Code migration (Vals AI)37.9%0.3%GLM 5.2
ProgramBench (Vals AI)0.5%Not measuredOnly GLM 5.2 measured
Terminal-Bench 2.1 (Vals AI)67.8%44.2%GLM 5.2
SkillsBench (Vals AI)45.1%Not measuredOnly GLM 5.2 measured
SciCode51.2%Not measuredOnly GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)50.8%37.9%GLM 5.2
Terminal-BenchNot measured57.3%Only Grok 4.20 measured
FrontierCode24.5%Not measuredOnly GLM 5.2 measured
WeirdML70.1%52.3%GLM 5.2
ALE-Bench1047.0Not measuredOnly GLM 5.2 measured
LMArena Text: coding1487Not measuredOnly GLM 5.2 measured
LMArena Text: software and IT1486Not measuredOnly GLM 5.2 measured
LMArena WebDev: React1617Not measuredOnly GLM 5.2 measured
LMArena WebDev: HTML1565Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
AA Intelligence Index33.725.7GLM 5.2
Epoch Capabilities Index151.9152.1Grok 4.20
Agentic workLike-for-likePublic boards, shown as published, kept out of the index101
Agentic work benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
AA Agentic Index38.4Not measuredOnly GLM 5.2 measured
Design Arena: agents building web apps12221144GLM 5.2
Design Arena: agents building full-stack apps12411054GLM 5.2
Design Arena: agents building mobile apps11601090GLM 5.2
Design Arena: agents building Android apps11841052GLM 5.2
Design Arena: agents building Godot games11421089GLM 5.2
Design Arena: agents building games1206Not measuredOnly GLM 5.2 measured
Design Arena: HTML slides11751180Grok 4.20
Design Arena: PowerPoint slides1195Not measuredOnly GLM 5.2 measured
SREBench (Vals AI)0.0%Not measuredOnly GLM 5.2 measured
Finance Agent (Vals AI)49.7%28.5%GLM 5.2
Tax Agent Bench (Vals AI)Not measured7.0%Only Grok 4.20 measured
Legal Research Bench (Vals AI)31.3%13.9%GLM 5.2
Excel Modeling Benchmark (Vals AI)61.5%11.7%GLM 5.2
τ²-Bench Telecom99.1%93.0%GLM 5.2
APEX-Agents45.2%Not measuredOnly GLM 5.2 measured
PostTrainBench31.7%Not measuredOnly GLM 5.2 measured
Vending-Bench 2$8,314$4,663GLM 5.2
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
GPQA Diamond85.6%88.6%Grok 4.20
MMMU Pro (Vals AI)Not measured83.5%Only Grok 4.20 measured
GPQA Diamond (Artificial Analysis run)89.5%91.1%Grok 4.20
Humanity's Last Exam (Artificial Analysis run)41.1%34.5%GLM 5.2
GPQA Diamond (Epoch AI run)91.9%Not measuredOnly GLM 5.2 measured
ARC-AGI77.0%89.5%Grok 4.20
ARC-AGI-222.8%65.1%Grok 4.20
SimpleBench58.8%Not measuredOnly GLM 5.2 measured
Chess puzzles22.0%Not measuredOnly GLM 5.2 measured
Mystery game puzzles19.0%Not measuredOnly GLM 5.2 measured
EBR-bench9.5%Not measuredOnly GLM 5.2 measured
LMArena Text: hard prompts1481Not measuredOnly GLM 5.2 measured
LMArena Text: expert1487Not measuredOnly GLM 5.2 measured
LMArena Text: hard prompts in English1481Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
AIMENot measured96.5%Only Grok 4.20 measured
OTIS Mock AIME86.4%Not measuredOnly GLM 5.2 measured
FrontierMath, tiers 1 to 359.2%Not measuredOnly GLM 5.2 measured
FrontierMath, tier 429.3%Not measuredOnly GLM 5.2 measured
ProofBench35.0%Not measuredOnly GLM 5.2 measured
LMArena Text: math1483Not measuredOnly GLM 5.2 measured
LMArena Text: mathematical work1489Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
MMLU Pro86.7%86.3%GLM 5.2
LegalBench (Vals AI)84.1%77.7%GLM 5.2
CaseLaw (Vals AI)Not measured54.4%Only Grok 4.20 measured
CorpFin (Vals AI)66.1%63.7%GLM 5.2
TaxEval (Vals AI)73.3%74.1%Grok 4.20
MortgageTax (Vals AI)Not measured45.4%Only Grok 4.20 measured
MedQA (Vals AI)Not measured94.5%Only Grok 4.20 measured
MedCode (Vals AI)40.8%32.2%GLM 5.2
SimpleQA Verified34.2%Not measuredOnly GLM 5.2 measured
LMArena Text: science1489Not measuredOnly GLM 5.2 measured
LMArena Text: medicine and healthcare1475Not measuredOnly GLM 5.2 measured
LMArena Text: legal and government1486Not measuredOnly GLM 5.2 measured
LMArena Text: business and finance1451Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
Design Arena: websites12851229GLM 5.2
Design Arena: UI components12961199GLM 5.2
Design Arena: game dev12681192GLM 5.2
Design Arena: data viz12851217GLM 5.2
Design Arena: 3D12881193GLM 5.2
Design Arena: all code categories12881221GLM 5.2
Design Arena: SVG12141164GLM 5.2
Design Arena: ASCII art11901174GLM 5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index41
General benchmarks for GLM 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
SAGE (Vals AI)Not measured38.2%Only Grok 4.20 measured
MedScribe (Vals AI)83.5%63.4%GLM 5.2
Vals Multimodal IndexNot measured39.1%Only Grok 4.20 measured
IFBench73.3%81.2%Grok 4.20
Long context reasoning (AA-LCR)78.3%69.0%GLM 5.2
DTBench93.6%90.1%GLM 5.2
LMCA45.8%38.7%GLM 5.2
CL-benchNot measured22.2%Only Grok 4.20 measured
Surface Evolver Bench55.6%Not measuredOnly GLM 5.2 measured
CL-bench LifeNot measured11.9%Only Grok 4.20 measured
LMArena Text1470Not measuredOnly GLM 5.2 measured
LMArena Text: instruction following1466Not measuredOnly GLM 5.2 measured
LMArena Text: creative writing1463Not measuredOnly GLM 5.2 measured
LMArena Text: English1475Not measuredOnly GLM 5.2 measured
LMArena Text: non-English1459Not measuredOnly GLM 5.2 measured
LMArena Text: Chinese1522Not measuredOnly GLM 5.2 measured
LMArena Text: German1470Not measuredOnly GLM 5.2 measured
LMArena Text: Japanese1450Not measuredOnly GLM 5.2 measured
LMArena Text: Korean1440Not measuredOnly GLM 5.2 measured
LMArena Text: French1479Not measuredOnly GLM 5.2 measured
LMArena Text: Spanish1478Not measuredOnly GLM 5.2 measured
LMArena Text: Russian1468Not measuredOnly GLM 5.2 measured
LMArena Text: Polish1456Not measuredOnly GLM 5.2 measured
LMArena Text: multi-turn1469Not measuredOnly GLM 5.2 measured
LMArena Text: longer queries1480Not measuredOnly GLM 5.2 measured
LMArena Text: writing and language1463Not measuredOnly GLM 5.2 measured
LMArena Text: entertainment and media1450Not measuredOnly GLM 5.2 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 5.2 and Grok 4.20
BenchmarkGLM 5.2Grok 4.20Leader
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 5.2$0.0036Fits in one request
Grok 4.20$0.0025Fits in one request

Grok 4.20 costs less

Repository review

50K input + 3K output tokens

GLM 5.2$0.083Fits in one request
Grok 4.20$0.070Fits in one request

Grok 4.20 costs less

Agent loop

200K input + 10K output tokens

GLM 5.2$0.324Fits in one request
Grok 4.20$0.275Fits in one request

Grok 4.20 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 5.2 and Grok 4.20
SpecificationZ.ai GLM 5.2SpaceXAI Grok 4.20
MakerZ.aixAI
WeightsOpen weightsNo public weights listed
ReleasedJune 16, 2026March 31, 2026
Context window1.05M2M
Input $/Mtok$1.40$1.25
Output $/Mtok$4.40$2.50
Coding index61.133.3
Independent measurements behind it42
Cost per solved task$0.86$0.72
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.2 better than Grok 4.20 for coding?

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 33.3 for Grok 4.20. Pick Grok 4.20 when output tokens cost 1.8x less, or when a solved task costs $0.72 against $0.86.

Which is cheaper, GLM 5.2 or Grok 4.20?

GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, GLM 5.2 costs $0.86 and Grok 4.20 $0.72.

Which has the bigger context window, GLM 5.2 or Grok 4.20?

Grok 4.20, with 2M tokens against 1.05M.

How many benchmarks is the GLM 5.2 vs Grok 4.20 comparison based on?

43 benchmarks have a result for both models as of October 21, 2026. GLM 5.2's coding index rests on 4 independent benchmarks and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/glm-5-2-vs-grok-4-20" title="GLM 5.2 vs Grok 4.20, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/glm-5-2-vs-grok-4-20">LLMBenchmark.ai, GLM 5.2 vs Grok 4.20</a></p>