Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GLM 5.3

GLM 5.3 leads Claude Sonnet 4.6 on coding, 70.6 to 57.3 on the Vibe Coding Index, and GLM 5.3 costs 3.4x less per output token ($4.40 vs $15.00 per million). Updated October 22, 2026; 83 benchmarks have a result for both.

Replace Claude Sonnet 4.6 Replace GLM 5.3
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
16
GLM 5.3Z.ai
Coding
70.6
Overall
67.9
Output $/M
$4.40
67
vs boards won of 83 shared

Claude Sonnet 4.6 or GLM 5.3: which to pick

Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 for work measured by LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Model AClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved taskModel BGLM 5.3Z.ai70.6/1006 independent benchmarks$0.36 per solved task
Shared results
83
Claude Sonnet 4.6 only
35
GLM 5.3 only
17
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
Claude Sonnet 4.6 57.3 from 5 benchmarks, GLM 5.3 70.6 from 6 benchmarks.
Widest category
Agentic work, 15.1 points apart on average over 11 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 4.6 68.0% against GLM 5.3 0.0%, 68.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GLM 5.3 $4.40 per million output tokens, 3.4x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GLM 5.3 1.05M.

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
CategoryClaude Sonnet 4.6BarsGLM 5.3Ties
Coding314
Intelligence02
Agentic work38
Reasoning19
Math04
Knowledge35
Web design27
General418
All shared boards1667
CodingLike-for-likeSix of these boards feed the Vibe Coding Index314
Coding benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
LiveBench coding66.6%82.8%GLM 5.3
LMArena WebDev15231621GLM 5.3
AA Coding Index63.074.8GLM 5.3
LiveCodeBench (Vals AI)82.1%80.5%Claude Sonnet 4.6
SWE-bench Verified (Vals AI)77.4%95.4%GLM 5.3
Terminal-Bench 4 (Vals AI)Not measured38.9%Only GLM 5.3 measured
Vibe Code Bench (Vals AI)55.8%78.1%GLM 5.3
Code migration (Vals AI)39.9%44.2%GLM 5.3
ProgramBench (Vals AI)0.5%1.5%GLM 5.3
IOI (Vals AI)Not measured68.4%Only GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)57.3%71.5%GLM 5.3
Vibe Code Bench 1-100 (Vals AI)Not measured20.0%Only GLM 5.3 measured
SkillsBench (Vals AI)49.0%47.5%Claude Sonnet 4.6
CyberBench (Vals AI)Not measured72.1%Only GLM 5.3 measured
SciCode50.1%59.0%GLM 5.3
Terminal-Bench Hard (Artificial Analysis run)53.0%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%40.1%GLM 5.3
FrontierSWENot measured30.2%Only GLM 5.3 measured
WeirdML66.1%75.4%GLM 5.3
ALE-BenchNot measured1317.4Only GLM 5.3 measured
LMArena Text: coding15031497Claude Sonnet 4.6
LMArena Text: software and IT14911493GLM 5.3
LMArena WebDev: React15121641GLM 5.3
LMArena WebDev: HTML15271595GLM 5.3
LMArena WebDev: from an image1529Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
AA Intelligence Index30.144.8GLM 5.3
Epoch Capabilities Index152.8156.0GLM 5.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index38
Agentic work benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
AA Agentic Index31.853.1GLM 5.3
Design Arena: agents building web apps1190Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building full-stack apps1213Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building mobile apps12121194Claude Sonnet 4.6
Design Arena: agents building Android apps1197Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building Godot games1226Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building games1177Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1230Only GLM 5.3 measured
LiveBench research63.6%73.2%GLM 5.3
LiveBench browser68.0%0.0%Claude Sonnet 4.6
LiveBench long agentic23.1%35.9%GLM 5.3
SREBench (Vals AI)Not measured9.2%Only GLM 5.3 measured
Finance Agent (Vals AI)51.0%55.8%GLM 5.3
Tax Agent Bench (Vals AI)25.8%39.7%GLM 5.3
Legal Research Bench (Vals AI)38.5%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)Not measured14.6%Only GLM 5.3 measured
Excel Modeling Benchmark (Vals AI)60.2%56.3%Claude Sonnet 4.6
Terminal-Bench-Science (Vals AI)Not measured5.7%Only GLM 5.3 measured
τ²-Bench Telecom79.5%Not measuredOnly Claude Sonnet 4.6 measured
APEX-Agents43.0%56.6%GLM 5.3
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204$8,164GLM 5.3
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index19
Reasoning benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
GPQA Diamond85.6%88.1%GLM 5.3
LiveBench reasoning86.4%85.8%Claude Sonnet 4.6
MysteryMechanism (Vals AI)Not measured23.0%Only GLM 5.3 measured
MMMU Pro (Vals AI)83.6%Not measuredOnly Claude Sonnet 4.6 measured
GPQA Diamond (Artificial Analysis run)87.5%91.7%GLM 5.3
Humanity's Last Exam (Artificial Analysis run)33.6%42.3%GLM 5.3
GPQA Diamond (Epoch AI run)87.4%90.9%GLM 5.3
ARC-AGI86.5%Not measuredOnly Claude Sonnet 4.6 measured
ARC-AGI-260.4%Not measuredOnly Claude Sonnet 4.6 measured
Chess puzzles23.0%37.0%GLM 5.3
Mystery game puzzles16.0%33.0%GLM 5.3
LMArena Text: hard prompts14851490GLM 5.3
LMArena Text: expert15001514GLM 5.3
LMArena Text: hard prompts in English14931496GLM 5.3
LMArena Vision: diagrams1306Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%91.1%GLM 5.3
FrontierMath, tiers 1 to 3Not measured68.8%Only GLM 5.3 measured
FrontierMath, tier 4Not measured29.3%Only GLM 5.3 measured
ProofBench45.0%49.0%GLM 5.3
LMArena Text: math14621495GLM 5.3
LMArena Text: mathematical work14831497GLM 5.3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index35
Knowledge benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
MMLU Pro87.3%86.8%Claude Sonnet 4.6
LegalBench (Vals AI)82.1%84.8%GLM 5.3
CaseLaw (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.6 measured
CorpFin (Vals AI)65.3%Not measuredOnly Claude Sonnet 4.6 measured
TaxEval (Vals AI)77.1%72.4%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%Not measuredOnly Claude Sonnet 4.6 measured
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured42.9%Only GLM 5.3 measured
SimpleQA Verified35.5%41.0%GLM 5.3
LMArena Text: science14741498GLM 5.3
LMArena Text: medicine and healthcare14511481GLM 5.3
LMArena Text: legal and government14701473GLM 5.3
LMArena Text: business and finance14641459Claude Sonnet 4.6
FACTS Benchmark Suite37.0%Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index27
Web design benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
Design Arena: websites12841295GLM 5.3
Design Arena: UI components12691314GLM 5.3
Design Arena: game dev12581311GLM 5.3
Design Arena: data viz12781260Claude Sonnet 4.6
Design Arena: 3D12341332GLM 5.3
Design Arena: all code categories12751304GLM 5.3
Design Arena: SVG11961294GLM 5.3
Design Arena: ASCII art12351208Claude Sonnet 4.6
LiveBench design71.8%77.3%GLM 5.3
GeneralLike-for-likePublic boards, shown as published, kept out of the index418
General benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
Vals IndexNot measured59.7%Only GLM 5.3 measured
LiveBench data analysis76.1%70.2%Claude Sonnet 4.6
Public Benefits Bench (Vals AI)62.5%68.5%GLM 5.3
SAGE (Vals AI)46.6%Not measuredOnly Claude Sonnet 4.6 measured
MedScribe (Vals AI)Not measured88.8%Only GLM 5.3 measured
Vals Multimodal Index60.6%Not measuredOnly Claude Sonnet 4.6 measured
IFBench56.6%Not measuredOnly Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)80.0%79.7%Claude Sonnet 4.6
DTBench89.9%87.7%Claude Sonnet 4.6
LMCA46.5%55.5%GLM 5.3
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581474GLM 5.3
LMArena Text: instruction following14761479GLM 5.3
LMArena Text: creative writing14351458GLM 5.3
LMArena Vision1283Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text: English14721482GLM 5.3
LMArena Text: non-English14401459GLM 5.3
LMArena Text: Chinese14911532GLM 5.3
LMArena Text: German14281488GLM 5.3
LMArena Text: Japanese14201460GLM 5.3
LMArena Text: Korean14101460GLM 5.3
LMArena Text: French14651503GLM 5.3
LMArena Text: Spanish14641462Claude Sonnet 4.6
LMArena Text: Russian14401469GLM 5.3
LMArena Text: Polish14431466GLM 5.3
LMArena Text: multi-turn14641472GLM 5.3
LMArena Text: longer queries14791483GLM 5.3
LMArena Text: writing and language14441469GLM 5.3
LMArena Text: entertainment and media14311447GLM 5.3
LMArena Vision: English1298Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: Chinese1307Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: reading text1296Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: humor1248Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: recognizing things1195Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: creative writing1272Not measuredOnly Claude Sonnet 4.6 measured
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.6 and GLM 5.3
BenchmarkClaude Sonnet 4.6GLM 5.3Leader
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

Claude Sonnet 4.6$0.011Fits in one request
GLM 5.3$0.0036Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GLM 5.3$0.083Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GLM 5.3$0.324Fits in one request

GLM 5.3 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 Claude Sonnet 4.6 and GLM 5.3
SpecificationAnthropic Claude Sonnet 4.6Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedFebruary 17, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$3.00$1.40
Output $/Mtok$15.00$4.40
Coding index57.370.6
Independent measurements behind it56
Cost per solved task$1.68$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than GLM 5.3 for coding?

Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 for work measured by LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 4.6 or GLM 5.3?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GLM 5.3 costs $1.40 and $4.40. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and GLM 5.3 $0.36.

Which has the bigger context window, Claude Sonnet 4.6 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs GLM 5.3 comparison based on?

83 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.6's coding index rests on 5 independent benchmarks and GLM 5.3's on 6. 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/claude-sonnet-4-6-vs-glm-5-3" title="Claude Sonnet 4.6 vs GLM 5.3, 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/claude-sonnet-4-6-vs-glm-5-3">LLMBenchmark.ai, Claude Sonnet 4.6 vs GLM 5.3</a></p>