Enter opens the highlighted result. Esc closes.

Claude Sonnet 5.5 vs GLM 5.3

Claude Sonnet 5.5 leads GLM 5.3 on coding, 87.3 to 70.6 on the Vibe Coding Index, and GLM 5.3 costs 2.3x less per output token ($4.40 vs $10.00 per million). Updated October 21, 2026; 80 benchmarks have a result for both.

Replace Claude Sonnet 5.5 Replace GLM 5.3
Claude Sonnet 5.5Anthropic
Coding
87.3
Overall
82.8
Output $/M
$10.00
67
GLM 5.3Z.ai
Coding
70.6
Overall
67.9
Output $/M
$4.40
13
vs boards won of 80 shared

Claude Sonnet 5.5 or GLM 5.3: which to pick

Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 70.6 for GLM 5.3, though on 5 benchmarks against 6.

Pick GLM 5.3 for output tokens 2.3x cheaper ($4.40 vs $10.00 per million) and a larger context window (1.05M against 1M tokens).

Model AClaude Sonnet 5.5Anthropic87.3/1005 independent benchmarksNo cost per solved taskModel BGLM 5.3Z.ai70.6/1006 independent benchmarks$0.36 per solved task
Shared results
80
Claude Sonnet 5.5 only
16
GLM 5.3 only
20
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 5.5 87.3 from 5 benchmarks, GLM 5.3 70.6 from 6 benchmarks.
Widest category
Math, 22.3 points apart on average over 6 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 5.5 84.0% against GLM 5.3 0.0%, 84.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5.5 $10.00 against GLM 5.3 $4.40 per million output tokens, 2.3x apart.
Context window
Claude Sonnet 5.5 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 5.5BarsGLM 5.3Ties
Coding161
Intelligence20
Agentic work112
Reasoning90
Math60
Knowledge42
Web design70
General128
All shared boards6713
CodingLike-for-likeSix of these boards feed the Vibe Coding Index161
Coding benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
LiveBench coding94.7%82.8%Claude Sonnet 5.5
LMArena WebDev17681621Claude Sonnet 5.5
AA Coding IndexNot measured74.8Only GLM 5.3 measured
LiveCodeBench (Vals AI)Not measured80.5%Only GLM 5.3 measured
SWE-bench Verified (Vals AI)Not measured95.4%Only GLM 5.3 measured
Terminal-Bench 4 (Vals AI)64.1%38.9%Claude Sonnet 5.5
Vibe Code Bench (Vals AI)92.4%78.1%Claude Sonnet 5.5
Code migration (Vals AI)69.8%44.2%Claude Sonnet 5.5
ProgramBench (Vals AI)6.5%1.5%Claude Sonnet 5.5
IOI (Vals AI)83.1%68.4%Claude Sonnet 5.5
Terminal-Bench 2.1 (Vals AI)83.2%71.5%Claude Sonnet 5.5
SWE-bench Multimodal (Vals AI)58.3%Not measuredOnly Claude Sonnet 5.5 measured
Vibe Code Bench 1-100 (Vals AI)Not measured20.0%Only GLM 5.3 measured
SkillsBench (Vals AI)Not measured47.5%Only GLM 5.3 measured
CyberBench (Vals AI)59.6%72.1%GLM 5.3
SciCode61.0%59.0%Claude Sonnet 5.5
FrontierCode52.1%40.1%Claude Sonnet 5.5
FrontierSWE61.9%30.2%Claude Sonnet 5.5
WeirdMLNot measured75.4%Only GLM 5.3 measured
ALE-Bench1819.11317.4Claude Sonnet 5.5
LMArena Text: coding15131497Claude Sonnet 5.5
LMArena Text: software and IT15041493Claude Sonnet 5.5
LMArena WebDev: React18171641Claude Sonnet 5.5
LMArena WebDev: HTML17411595Claude Sonnet 5.5
LMArena WebDev: from an image1737Not measuredOnly Claude Sonnet 5.5 measured
SciCode13.8%Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
AA Intelligence Index56.044.8Claude Sonnet 5.5
Epoch Capabilities Index166.2156.0Claude Sonnet 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index112
Agentic work benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
AA Agentic IndexNot measured53.1Only GLM 5.3 measured
Design Arena: agents building web apps1306Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: agents building mobile apps12571194Claude Sonnet 5.5
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1254Only GLM 5.3 measured
Design Arena: spreadsheets1244Not measuredOnly Claude Sonnet 5.5 measured
LiveBench research83.6%73.2%Claude Sonnet 5.5
LiveBench browser84.0%0.0%Claude Sonnet 5.5
LiveBench long agentic78.8%35.9%Claude Sonnet 5.5
SREBench (Vals AI)30.1%9.2%Claude Sonnet 5.5
Finance Agent (Vals AI)58.1%55.8%Claude Sonnet 5.5
Tax Agent Bench (Vals AI)42.0%39.7%Claude Sonnet 5.5
Legal Research Bench (Vals AI)48.1%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)10.4%14.6%GLM 5.3
Excel Modeling Benchmark (Vals AI)75.7%56.3%Claude Sonnet 5.5
BioMysteryBench (Vals AI)81.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%5.7%Claude Sonnet 5.5
Vals Science Index59.1%Not measuredOnly Claude Sonnet 5.5 measured
APEX-Agents75.5%56.6%Claude Sonnet 5.5
SpireClimb1.3%Not measuredOnly Claude Sonnet 5.5 measured
Vending-Bench 2$11,165$8,164Claude Sonnet 5.5
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
GPQA DiamondNot measured88.1%Only GLM 5.3 measured
LiveBench reasoning91.6%85.8%Claude Sonnet 5.5
MysteryMechanism (Vals AI)49.1%23.0%Claude Sonnet 5.5
GPQA Diamond (Artificial Analysis run)Not measured91.7%Only GLM 5.3 measured
Humanity's Last Exam (Artificial Analysis run)55.0%42.3%Claude Sonnet 5.5
GPQA Diamond (Epoch AI run)95.6%90.9%Claude Sonnet 5.5
Chess puzzles59.0%37.0%Claude Sonnet 5.5
Mystery game puzzles65.0%33.0%Claude Sonnet 5.5
LMArena Text: hard prompts14941490Claude Sonnet 5.5
LMArena Text: expert15311514Claude Sonnet 5.5
LMArena Text: hard prompts in English15021496Claude Sonnet 5.5
LMArena Vision: diagrams1329Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: homework1331Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
OTIS Mock AIME100.0%91.1%Claude Sonnet 5.5
FrontierMath, tiers 1 to 388.8%68.8%Claude Sonnet 5.5
FrontierMath, tier 480.5%29.3%Claude Sonnet 5.5
ProofBench100.0%49.0%Claude Sonnet 5.5
LMArena Text: math14971495Claude Sonnet 5.5
LMArena Text: mathematical work15101497Claude Sonnet 5.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index42
Knowledge benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
MMLU ProNot measured86.8%Only GLM 5.3 measured
LegalBench (Vals AI)Not measured84.8%Only GLM 5.3 measured
TaxEval (Vals AI)Not measured72.4%Only GLM 5.3 measured
MedCode (Vals AI)52.9%42.9%Claude Sonnet 5.5
SimpleQA Verified46.5%41.0%Claude Sonnet 5.5
LMArena Text: science14831498GLM 5.3
LMArena Text: medicine and healthcare14641481GLM 5.3
LMArena Text: legal and government14831473Claude Sonnet 5.5
LMArena Text: business and finance14681459Claude Sonnet 5.5
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
Design Arena: websites13261295Claude Sonnet 5.5
Design Arena: UI components13651314Claude Sonnet 5.5
Design Arena: game dev14691311Claude Sonnet 5.5
Design Arena: data viz13941259Claude Sonnet 5.5
Design Arena: 3D14521332Claude Sonnet 5.5
Design Arena: all code categories13641304Claude Sonnet 5.5
Design Arena: SVGNot measured1293Only GLM 5.3 measured
Design Arena: ASCII artNot measured1213Only GLM 5.3 measured
LiveBench design85.0%77.3%Claude Sonnet 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index128
General benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 5.3Leader
Vals Index70.8%59.7%Claude Sonnet 5.5
LiveBench data analysis59.5%70.2%GLM 5.3
Public Benefits Bench (Vals AI)67.2%68.5%GLM 5.3
SAGE (Vals AI)51.8%Not measuredOnly Claude Sonnet 5.5 measured
MedScribe (Vals AI)91.1%88.8%Claude Sonnet 5.5
Long context reasoning (AA-LCR)82.7%79.7%Claude Sonnet 5.5
DTBench97.3%87.7%Claude Sonnet 5.5
LMCA68.3%55.5%Claude Sonnet 5.5
Furniture assembly75.0%Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text14731474GLM 5.3
LMArena Text: instruction following14921479Claude Sonnet 5.5
LMArena Text: creative writing14671458Claude Sonnet 5.5
LMArena Vision1287Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text: English14841482Claude Sonnet 5.5
LMArena Text: non-English14561459GLM 5.3
LMArena Text: Chinese15351532Claude Sonnet 5.5
LMArena Text: GermanNot measured1488Only GLM 5.3 measured
LMArena Text: JapaneseNot measured1460Only GLM 5.3 measured
LMArena Text: KoreanNot measured1460Only GLM 5.3 measured
LMArena Text: French14991503GLM 5.3
LMArena Text: Spanish14511462GLM 5.3
LMArena Text: Russian14541469GLM 5.3
LMArena Text: PolishNot measured1466Only GLM 5.3 measured
LMArena Text: multi-turn14651472GLM 5.3
LMArena Text: longer queries14951483Claude Sonnet 5.5
LMArena Text: writing and language14741469Claude Sonnet 5.5
LMArena Text: entertainment and media14611447Claude Sonnet 5.5
LMArena Vision: English1289Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: reading text1297Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: creative writing1242Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5.5 and GLM 5.3
BenchmarkClaude Sonnet 5.5GLM 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 5.5$0.0070Fits 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 5.5$0.130Fits 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 5.5$0.500Fits 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 5.5 and GLM 5.3
SpecificationAnthropic Claude Sonnet 5.5Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedSeptember 28, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$2.00$1.40
Output $/Mtok$10.00$4.40
Coding index87.370.6
Independent measurements behind it56
Cost per solved taskNot computable$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5.5 better than GLM 5.3 for coding?

Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 70.6 for GLM 5.3, though on 5 benchmarks against 6. Pick GLM 5.3 for output tokens 2.3x cheaper ($4.40 vs $10.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Sonnet 5.5 or GLM 5.3?

Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; GLM 5.3 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.3 only.

Which has the bigger context window, Claude Sonnet 5.5 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5.5 vs GLM 5.3 comparison based on?

80 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5.5'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-5-5-vs-glm-5-3" title="Claude Sonnet 5.5 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-5-5-vs-glm-5-3">LLMBenchmark.ai, Claude Sonnet 5.5 vs GLM 5.3</a></p>