LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs GLM 5.3

Updated October 21, 2026. 96 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5 Replace GLM 5.3
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
26
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
68
vs boards won of 96 shared, 2 tied

Decision reading

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 63.5 for Claude Sonnet 5.

Pick Claude Sonnet 5 when what matters is LiveCodeBench (Vals AI) or Vibe Code Bench (Vals AI), where it leads.

Model AClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved taskModel BGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved task
Shared results
96
Claude Sonnet 5 only
24
GLM 5.3 only
4
Like-for-like categories
8 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
Claude Sonnet 5 63.5 from 2 benchmarks, GLM 5.3 73.1 from 2 benchmarks.
Widest category
Agentic work, 10.5 points apart on average over 15 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 5 72.0% against GLM 5.3 0.0%, 72.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against GLM 5.3 $1.40 per million output tokens, 7.1x apart.
Context window
Claude Sonnet 5 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 5BarsGLM 5.3Ties
Coding616
Intelligence11
Agentic work681 tie
Reasoning46
Math231 tie
Knowledge36
Web design18
General320
All shared boards26682 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index616
Coding benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
LiveBench coding74.7%82.8%GLM 5.3
LMArena WebDev15401621GLM 5.3
AA Coding Index71.574.8GLM 5.3
LiveCodeBench (Vals AI)82.4%80.5%Claude Sonnet 5
SWE-bench Verified (Vals AI)79.6%95.4%GLM 5.3
Terminal-Bench 4 (Vals AI)10.6%38.9%GLM 5.3
Vibe Code Bench (Vals AI)81.3%78.1%Claude Sonnet 5
Code migration (Vals AI)44.4%44.2%Claude Sonnet 5
ProgramBench (Vals AI)0.0%1.5%GLM 5.3
IOI (Vals AI)45.0%68.4%GLM 5.3
Terminal-Bench 2.1 (Vals AI)74.5%71.5%Claude Sonnet 5
Vibe Code Bench 1-100 (Vals AI)13.8%20.0%GLM 5.3
SkillsBench (Vals AI)46.5%47.5%GLM 5.3
CyberBench (Vals AI)70.3%72.1%GLM 5.3
SciCode54.3%59.0%GLM 5.3
FrontierCode42.7%40.1%Claude Sonnet 5
FrontierSWENot measured30.2%Only GLM 5.3 measured
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%75.4%GLM 5.3
ALE-Bench1463.11317.4Claude Sonnet 5
LMArena Text: coding14831497GLM 5.3
LMArena Text: software and IT14741493GLM 5.3
LMArena WebDev: React15411641GLM 5.3
LMArena WebDev: HTML15271595GLM 5.3
LMArena WebDev: from an image1540Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
AA Intelligence Index38.244.8GLM 5.3
Epoch Capabilities Index156.9156.0Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index68
Agentic work benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
AA Agentic Index43.653.1GLM 5.3
Design Arena: agents building web apps1245Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building mobile apps12151194Claude Sonnet 5
Design Arena: agents building Android apps1231Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building Godot games1225Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building games1227Not measuredOnly Claude Sonnet 5 measured
Design Arena: HTML slides12181189Claude Sonnet 5
Design Arena: PowerPoint slides12161255GLM 5.3
Design Arena: spreadsheets1004Not measuredOnly Claude Sonnet 5 measured
LiveBench research82.8%73.2%Claude Sonnet 5
LiveBench browser72.0%0.0%Claude Sonnet 5
LiveBench long agentic39.0%35.9%Claude Sonnet 5
SREBench (Vals AI)0.4%9.2%GLM 5.3
Finance Agent (Vals AI)53.9%55.8%GLM 5.3
Tax Agent Bench (Vals AI)29.4%39.7%GLM 5.3
Legal Research Bench (Vals AI)41.8%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)66.3%56.3%Claude Sonnet 5
Terminal-Bench-Science (Vals AI)5.7%5.7%Tie
APEX-Agents54.5%56.6%GLM 5.3
Vending-Bench 2$6,378$8,164GLM 5.3
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index46
Reasoning benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
GPQA Diamond88.9%88.1%Claude Sonnet 5
LiveBench reasoning88.7%85.8%Claude Sonnet 5
MysteryMechanism (Vals AI)Not measured23.0%Only GLM 5.3 measured
MMMU Pro (Vals AI)83.0%Not measuredOnly Claude Sonnet 5 measured
GPQA Diamond (Artificial Analysis run)91.1%91.7%GLM 5.3
Humanity's Last Exam (Artificial Analysis run)41.3%42.3%GLM 5.3
GPQA Diamond (Epoch AI run)90.5%90.9%GLM 5.3
SimpleBench60.6%Not measuredOnly Claude Sonnet 5 measured
Chess puzzles45.0%37.0%Claude Sonnet 5
Mystery game puzzles35.0%33.0%Claude Sonnet 5
LMArena Text: hard prompts14611490GLM 5.3
LMArena Text: expert14891514GLM 5.3
LMArena Text: hard prompts in English14641496GLM 5.3
LMArena Vision: diagrams1293Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index23
Math benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
OTIS Mock AIME94.7%91.1%Claude Sonnet 5
FrontierMath, tiers 1 to 365.6%68.8%GLM 5.3
FrontierMath, tier 429.3%29.3%Tie
ProofBench77.0%49.0%Claude Sonnet 5
LMArena Text: math14671495GLM 5.3
LMArena Text: mathematical work14811497GLM 5.3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
Knowledge benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
MMLU Pro87.5%86.8%Claude Sonnet 5
LegalBench (Vals AI)83.9%84.8%GLM 5.3
CorpFin (Vals AI)67.0%Not measuredOnly Claude Sonnet 5 measured
TaxEval (Vals AI)75.6%72.4%Claude Sonnet 5
MortgageTax (Vals AI)70.0%Not measuredOnly Claude Sonnet 5 measured
MedCode (Vals AI)47.5%42.9%Claude Sonnet 5
SimpleQA Verified33.7%41.0%GLM 5.3
LMArena Text: science14601498GLM 5.3
LMArena Text: medicine and healthcare14421481GLM 5.3
LMArena Text: legal and government14541473GLM 5.3
LMArena Text: business and finance14361459GLM 5.3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index18
Web design benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
Design Arena: websites12741295GLM 5.3
Design Arena: UI components12791314GLM 5.3
Design Arena: game dev12781311GLM 5.3
Design Arena: data viz12511260GLM 5.3
Design Arena: 3D12611332GLM 5.3
Design Arena: all code categories12761304GLM 5.3
Design Arena: SVG11931292GLM 5.3
Design Arena: ASCII art12071213GLM 5.3
LiveBench design82.0%77.3%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index320
General benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 5.3Leader
Vals IndexNot measured59.7%Only GLM 5.3 measured
LiveBench data analysis71.7%70.2%Claude Sonnet 5
Public Benefits Bench (Vals AI)66.0%68.5%GLM 5.3
SAGE (Vals AI)48.9%Not measuredOnly Claude Sonnet 5 measured
MedScribe (Vals AI)76.0%88.8%GLM 5.3
Vals Multimodal Index68.8%Not measuredOnly Claude Sonnet 5 measured
Long context reasoning (AA-LCR)82.0%79.7%Claude Sonnet 5
DTBench92.5%87.7%Claude Sonnet 5
LMCA50.0%55.5%GLM 5.3
Surface Evolver Bench60.0%Not measuredOnly Claude Sonnet 5 measured
LMArena Text14421474GLM 5.3
LMArena Text: instruction following14521479GLM 5.3
LMArena Text: creative writing14161458GLM 5.3
LMArena Vision1273Not measuredOnly Claude Sonnet 5 measured
LMArena Text: English14501482GLM 5.3
LMArena Text: non-English14311459GLM 5.3
LMArena Text: Chinese14781532GLM 5.3
LMArena Text: German14421488GLM 5.3
LMArena Text: Japanese14221460GLM 5.3
LMArena Text: Korean14121460GLM 5.3
LMArena Text: French14631503GLM 5.3
LMArena Text: Spanish14381462GLM 5.3
LMArena Text: Russian14501469GLM 5.3
LMArena Text: Polish14251466GLM 5.3
LMArena Text: multi-turn14531472GLM 5.3
LMArena Text: longer queries14621483GLM 5.3
LMArena Text: writing and language14361469GLM 5.3
LMArena Text: entertainment and media14111447GLM 5.3
LMArena Vision: English1275Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: Chinese1331Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: reading text1288Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: humor1261Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: creative writing1246Not measuredOnly Claude Sonnet 5 measured
LMArena Document1466Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5 and GLM 5.3
BenchmarkClaude Sonnet 5GLM 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 5$0.0070Fits in one request
GLM 5.3$0.0008Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
GLM 5.3$0.0081Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
GLM 5.3$0.030Fits 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 5 and GLM 5.3
SpecificationAnthropic Claude Sonnet 5Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedJune 30, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.079
Output $/Mtok$10.00$1.40
Coding index63.573.1
Independent measurements behind it22
Cost per solved task$1.87$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than GLM 5.3 for coding?

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 63.5 for Claude Sonnet 5. Pick Claude Sonnet 5 when what matters is LiveCodeBench (Vals AI) or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 5 or GLM 5.3?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; GLM 5.3 costs $0.079 and $1.40. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and GLM 5.3 $0.36.

Which has the bigger context window, Claude Sonnet 5 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5 vs GLM 5.3 comparison based on?

96 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5's coding index rests on 2 independent benchmarks and GLM 5.3'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/claude-sonnet-5-vs-glm-5-3" title="Claude Sonnet 5 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-5-vs-glm-5-3">LLMBenchmark.ai, Claude Sonnet 5 vs GLM 5.3</a></p>