GLM 4.7 vs Grok 4.20

GLM 4.7 leads Grok 4.20 on coding, 55.1 to 33.3 on the Vibe Coding Index, at about the same output price ($2.20 vs $2.50 per million). Updated October 21, 2026; 36 benchmarks have a result for both.

Replace GLM 4.7 Replace Grok 4.20

GLM 4.7Z.ai

Coding: 55.1
Overall: 56.9
Output $/M: $2.20

Grok 4.20xAI

Coding: 33.3
Overall: 41.0
Output $/M: $2.50

vs boards won of 36 shared, 1 tied

GLM 4.7 or Grok 4.20: which to pick

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 33.3 for Grok 4.20.

Pick Grok 4.20 for a larger context window (2M against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Model AGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved task Model BGrok 4.20xAI33.3/1002 independent benchmarks$0.72 per solved task

364519

Shared results: 36
GLM 4.7 only: 45
Grok 4.20 only: 19
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.

Coding
Vibe Coding Index, six public coding benchmarks
GLM 4.7
GLM 4.7 scores 55.1 against 33.3.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Grok 4.20
Grok 4.20 leads, 25.7 against 22.2.
Same board, both measured
Reasoning
GPQA Diamond
Grok 4.20
Grok 4.20 leads, 88.6% against 80.0%.
Same board, both measured
Math
AIME
Grok 4.20
Grok 4.20 leads, 96.5% against 93.3%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.20
Grok 4.20 leads, 86.3% against 82.7%.
Same board, both measured
Web design
Design Arena: websites
Grok 4.20
Grok 4.20 leads, 1229 against 1226.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.7
GLM 4.7 $0.0017, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GLM 4.7
GLM 4.7 $0.29, Grok 4.20 $0.72.
Published attempt cost and pass rate

At a glance

Coding index: GLM 4.7 55.1 from 2 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
Widest category: Coding, 8.7 points apart on average over 4 shared benchmarks.
Widest single gap: Terminal-Bench: GLM 4.7 33.4% against Grok 4.20 57.3%, 23.9 points apart on a 0 to 100 scale.
Output price: GLM 4.7 $2.20 against Grok 4.20 $2.50 per million output tokens, 1.1x apart.
Context window: GLM 4.7 takes 205K 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
Category	GLM 4.7	Grok 4.20	Ties
Coding	0	4
Intelligence	0	2
Agentic work	3	3
Reasoning	0	3
Math	0	1
Knowledge	3	4
Web design	0	7	1 tie
General	2	3
All shared boards	8	27	1 tie

CodingLike-for-likeSix of these boards feed the Vibe Coding Index04

Coding benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
LMArena WebDev	1435	Not measured	Only GLM 4.7 measured
AA Coding Index	45.3	Not measured	Only GLM 4.7 measured
LiveCodeBench (Vals AI)	82.2%	84.3%	Grok 4.20
SWE-bench Verified (Vals AI)	69.4%	72.2%	Grok 4.20
Vibe Code Bench (Vals AI)	Not measured	4.1%	Only Grok 4.20 measured
Code migration (Vals AI)	Not measured	0.3%	Only Grok 4.20 measured
Terminal-Bench 2.1 (Vals AI)	Not measured	44.2%	Only Grok 4.20 measured
LiveCodeBench (Artificial Analysis run)	89.4%	Not measured	Only GLM 4.7 measured
Terminal-Bench Hard (Artificial Analysis run)	31.8%	37.9%	Grok 4.20
Terminal-Bench	33.4%	57.3%	Grok 4.20
WeirdML	Not measured	52.3%	Only Grok 4.20 measured
ALE-Bench	399.5	Not measured	Only GLM 4.7 measured
LMArena Text: coding	1454	Not measured	Only GLM 4.7 measured
LMArena Text: software and IT	1453	Not measured	Only GLM 4.7 measured
LMArena WebDev: React	1420	Not measured	Only GLM 4.7 measured
LMArena WebDev: HTML	1447	Not measured	Only 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 index02

Intelligence benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
AA Intelligence Index	22.2	25.7	Grok 4.20
Epoch Capabilities Index	143.6	152.1	Grok 4.20

Agentic workLike-for-likePublic boards, shown as published, kept out of the index33

Agentic work benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
Design Arena: agents building web apps	Not measured	1144	Only Grok 4.20 measured
Design Arena: agents building full-stack apps	1050	1054	Grok 4.20
Design Arena: agents building mobile apps	1105	1090	GLM 4.7
Design Arena: agents building Android apps	1112	1052	GLM 4.7
Design Arena: agents building Godot games	1058	1089	Grok 4.20
Design Arena: HTML slides	Not measured	1180	Only Grok 4.20 measured
Finance Agent (Vals AI)	Not measured	28.5%	Only Grok 4.20 measured
Tax Agent Bench (Vals AI)	Not measured	7.0%	Only Grok 4.20 measured
Legal Research Bench (Vals AI)	Not measured	13.9%	Only Grok 4.20 measured
Excel Modeling Benchmark (Vals AI)	Not measured	11.7%	Only Grok 4.20 measured
τ²-Bench Telecom	95.9%	93.0%	GLM 4.7
Vending-Bench 2	$2,377	$4,663	Grok 4.20
BrowseComp-Plus	64.7%	Not measured	Only GLM 4.7 measured
Neither model has a result on the other 28 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index03

Reasoning benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
GPQA Diamond	80.0%	88.6%	Grok 4.20
MMMU Pro (Vals AI)	Not measured	83.5%	Only Grok 4.20 measured
GPQA Diamond (Artificial Analysis run)	85.9%	91.1%	Grok 4.20
Humanity's Last Exam (Artificial Analysis run)	27.4%	34.5%	Grok 4.20
GPQA Diamond (Epoch AI run)	83.3%	Not measured	Only GLM 4.7 measured
ARC-AGI	Not measured	89.5%	Only Grok 4.20 measured
ARC-AGI-2	Not measured	65.1%	Only Grok 4.20 measured
SimpleBench	47.7%	Not measured	Only GLM 4.7 measured
Chess puzzles	21.0%	Not measured	Only GLM 4.7 measured
LMArena Text: hard prompts	1443	Not measured	Only GLM 4.7 measured
LMArena Text: expert	1424	Not measured	Only GLM 4.7 measured
LMArena Text: hard prompts in English	1452	Not measured	Only GLM 4.7 measured
Kagi LLM Benchmark	Not measured	75.0%	Only Grok 4.20 measured
Neither model has a result on the other 9 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index01

Math benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
AIME	93.3%	96.5%	Grok 4.20
MGSM (Vals AI)	88.2%	Not measured	Only GLM 4.7 measured
AA Math Index	95.0	Not measured	Only GLM 4.7 measured
AIME 2025 (Artificial Analysis run)	95.0%	Not measured	Only GLM 4.7 measured
OTIS Mock AIME	83.3%	Not measured	Only GLM 4.7 measured
ProofBench	6.0%	Not measured	Only GLM 4.7 measured
LMArena Text: math	1424	Not measured	Only GLM 4.7 measured
LMArena Text: mathematical work	1411	Not measured	Only GLM 4.7 measured
Neither model has a result on the other 5 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index34

Knowledge benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
MMLU Pro	82.7%	86.3%	Grok 4.20
LegalBench (Vals AI)	83.4%	77.7%	GLM 4.7
CaseLaw (Vals AI)	54.9%	54.4%	GLM 4.7
CorpFin (Vals AI)	46.4%	63.7%	Grok 4.20
TaxEval (Vals AI)	68.8%	74.1%	Grok 4.20
MortgageTax (Vals AI)	Not measured	45.4%	Only Grok 4.20 measured
MedQA (Vals AI)	93.7%	94.5%	Grok 4.20
MedCode (Vals AI)	32.8%	32.2%	GLM 4.7
MMLU Pro (Artificial Analysis run)	85.6%	Not measured	Only GLM 4.7 measured
SimpleQA Verified	32.2%	Not measured	Only GLM 4.7 measured
LMArena Text: science	1457	Not measured	Only GLM 4.7 measured
LMArena Text: medicine and healthcare	1469	Not measured	Only GLM 4.7 measured
LMArena Text: legal and government	1444	Not measured	Only GLM 4.7 measured
LMArena Text: business and finance	1429	Not measured	Only GLM 4.7 measured
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 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
Design Arena: websites	1226	1229	Grok 4.20
Design Arena: UI components	1199	1199	Tie
Design Arena: game dev	1189	1192	Grok 4.20
Design Arena: data viz	1195	1217	Grok 4.20
Design Arena: 3D	1191	1193	Grok 4.20
Design Arena: all code categories	1217	1221	Grok 4.20
Design Arena: SVG	1143	1164	Grok 4.20
Design Arena: ASCII art	1165	1174	Grok 4.20
Neither model has a result on the other 1 board here

GeneralLike-for-likePublic boards, shown as published, kept out of the index23

General benchmarks for GLM 4.7 and Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
SAGE (Vals AI)	Not measured	38.2%	Only Grok 4.20 measured
MedScribe (Vals AI)	68.6%	63.4%	GLM 4.7
Vals Multimodal Index	Not measured	39.1%	Only Grok 4.20 measured
IFBench	67.9%	81.2%	Grok 4.20
Long context reasoning (AA-LCR)	71.0%	69.0%	GLM 4.7
DTBench	Not measured	90.1%	Only Grok 4.20 measured
LMCA	Not measured	38.7%	Only Grok 4.20 measured
CL-bench	15.9%	22.2%	Grok 4.20
CL-bench Life	10.9%	11.9%	Grok 4.20
LMArena Text	1435	Not measured	Only GLM 4.7 measured
LMArena Text: instruction following	1412	Not measured	Only GLM 4.7 measured
LMArena Text: creative writing	1401	Not measured	Only GLM 4.7 measured
LMArena Text: English	1453	Not measured	Only GLM 4.7 measured
LMArena Text: non-English	1417	Not measured	Only GLM 4.7 measured
LMArena Text: Chinese	1495	Not measured	Only GLM 4.7 measured
LMArena Text: German	1426	Not measured	Only GLM 4.7 measured
LMArena Text: Japanese	1439	Not measured	Only GLM 4.7 measured
LMArena Text: Korean	1399	Not measured	Only GLM 4.7 measured
LMArena Text: French	1432	Not measured	Only GLM 4.7 measured
LMArena Text: Spanish	1434	Not measured	Only GLM 4.7 measured
LMArena Text: Russian	1423	Not measured	Only GLM 4.7 measured
LMArena Text: Polish	1435	Not measured	Only GLM 4.7 measured
LMArena Text: multi-turn	1446	Not measured	Only GLM 4.7 measured
LMArena Text: longer queries	1432	Not measured	Only GLM 4.7 measured
LMArena Text: writing and language	1411	Not measured	Only GLM 4.7 measured
LMArena Text: entertainment and media	1400	Not measured	Only GLM 4.7 measured
Neither model has a result on the other 20 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 Grok 4.20
Benchmark	GLM 4.7	Grok 4.20	Leader
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

Grok 4.20$0.0025Fits in one request

GLM 4.7 costs less

Repository review

50K input + 3K output tokens

GLM 4.7$0.037Fits in one request

Grok 4.20$0.070Fits in one request

GLM 4.7 costs less

Agent loop

200K input + 10K output tokens

GLM 4.7$0.142Exceeds the context window

Grok 4.20$0.275Fits in one request

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 4.7 and Grok 4.20
Specification	Z.ai GLM 4.7	SpaceXAI Grok 4.20
Maker	Z.ai	xAI
Weights	Open weights	No public weights listed
Released	December 22, 2025	March 31, 2026
Context window	205K	2M
Input $/Mtok	$0.60	$1.25
Output $/Mtok	$2.20	$2.50
Coding index	55.1	33.3
Independent measurements behind it	2	2
Cost per solved task	$0.29	$0.72
Source	OpenRouter listing	OpenRouter listing

Questions

Is GLM 4.7 better than Grok 4.20 for coding?

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 33.3 for Grok 4.20. Pick Grok 4.20 for a larger context window (2M against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, GLM 4.7 or Grok 4.20?

GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, GLM 4.7 costs $0.29 and Grok 4.20 $0.72.

Which has the bigger context window, GLM 4.7 or Grok 4.20?

Grok 4.20, with 2M tokens against 205K.

How many benchmarks is the GLM 4.7 vs Grok 4.20 comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. GLM 4.7's coding index rests on 2 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-4-7-vs-grok-4-20" title="GLM 4.7 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-4-7-vs-grok-4-20">LLMBenchmark.ai, GLM 4.7 vs Grok 4.20</a></p>

GLM 4.7 or Grok 4.20: which to pick

Which one for your work

Coding

Intelligence

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next