LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs GLM 5.3

Updated October 21, 2026. 91 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.8 Replace GLM 5.3
Claude Opus 4.8Anthropic
Coding
66.0
Overall
41.8
Output $/M
$25.00
39
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
52
vs boards won of 91 shared

Decision reading

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 66.0 for Claude Opus 4.8.

Pick Claude Opus 4.8 when what matters is LiveCodeBench (Vals AI) or Vibe Code Bench (Vals AI), where it leads.

Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved task
Shared results
91
Claude Opus 4.8 only
35
GLM 5.3 only
9
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 Opus 4.8 66.0 from 2 benchmarks, GLM 5.3 73.1 from 2 benchmarks.
Widest category
Agentic work, 13.8 points apart on average over 14 shared benchmarks.
Widest single gap
LiveBench browser: Claude Opus 4.8 96.0% against GLM 5.3 0.0%, 96.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against GLM 5.3 $1.40 per million output tokens, 17.9x apart.
Context window
Claude Opus 4.8 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 Opus 4.8BarsGLM 5.3Ties
Coding711
Intelligence11
Agentic work68
Reasoning73
Math51
Knowledge54
Web design27
General617
All shared boards3952
CodingLike-for-likeFour of these boards feed the Vibe Coding Index711
Coding benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
LiveBench coding77.3%82.8%GLM 5.3
LMArena WebDev15561621GLM 5.3
AA Coding Index74.374.8GLM 5.3
LiveCodeBench (Vals AI)87.8%80.5%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%95.4%GLM 5.3
Terminal-Bench 4 (Vals AI)23.2%38.9%GLM 5.3
Vibe Code Bench (Vals AI)82.7%78.1%Claude Opus 4.8
Code migration (Vals AI)47.3%44.2%Claude Opus 4.8
ProgramBench (Vals AI)1.0%1.5%GLM 5.3
IOI (Vals AI)Not measured68.4%Only GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)71.9%71.5%Claude Opus 4.8
Vibe Code Bench 1-100 (Vals AI)Not measured20.0%Only GLM 5.3 measured
SkillsBench (Vals AI)59.2%47.5%Claude Opus 4.8
CyberBench (Vals AI)Not measured72.1%Only GLM 5.3 measured
SciCode54.4%59.0%GLM 5.3
Terminal-Bench Hard (Artificial Analysis run)58.3%Not measuredOnly Claude Opus 4.8 measured
FrontierCode46.5%40.1%Claude Opus 4.8
FrontierSWENot measured30.2%Only GLM 5.3 measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%75.4%Claude Opus 4.8
ALE-BenchNot measured1317.4Only GLM 5.3 measured
LMArena Text: coding14901497GLM 5.3
LMArena Text: software and IT14881493GLM 5.3
LMArena WebDev: React15571641GLM 5.3
LMArena WebDev: HTML15431595GLM 5.3
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 Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
AA Intelligence Index41.844.8GLM 5.3
Epoch Capabilities Index159.0156.0Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index68
Agentic work benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
AA Agentic Index41.953.1GLM 5.3
Design Arena: agents building web apps1233Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building mobile apps12221194Claude Opus 4.8
Design Arena: agents building Android apps1237Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games1238Not measuredOnly Claude Opus 4.8 measured
Design Arena: HTML slides12211189Claude Opus 4.8
Design Arena: PowerPoint slides12271255GLM 5.3
LiveBench research81.8%73.2%Claude Opus 4.8
LiveBench browser96.0%0.0%Claude Opus 4.8
LiveBench long agentic48.3%35.9%Claude Opus 4.8
SREBench (Vals AI)Not measured9.2%Only GLM 5.3 measured
Finance Agent (Vals AI)53.9%55.8%GLM 5.3
Tax Agent Bench (Vals AI)30.0%39.7%GLM 5.3
Legal Research Bench (Vals AI)43.8%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)69.4%56.3%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%5.7%GLM 5.3
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%Not measuredOnly Claude Opus 4.8 measured
APEX-Agents48.9%56.6%GLM 5.3
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787$8,164GLM 5.3
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 11 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index73
Reasoning benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
GPQA Diamond92.4%88.1%Claude Opus 4.8
LiveBench reasoning89.2%85.8%Claude Opus 4.8
MysteryMechanism (Vals AI)Not measured23.0%Only GLM 5.3 measured
MMMU Pro (Vals AI)86.6%Not measuredOnly Claude Opus 4.8 measured
GPQA Diamond (Artificial Analysis run)92.0%91.7%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)48.7%42.3%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%90.9%Claude Opus 4.8
ARC-AGI92.5%Not measuredOnly Claude Opus 4.8 measured
ARC-AGI-272.1%Not measuredOnly Claude Opus 4.8 measured
SimpleBench64.8%Not measuredOnly Claude Opus 4.8 measured
Chess puzzles52.0%37.0%Claude Opus 4.8
Mystery game puzzles36.0%33.0%Claude Opus 4.8
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821490GLM 5.3
LMArena Text: expert15031514GLM 5.3
LMArena Text: hard prompts in English14871496GLM 5.3
LMArena Vision: diagrams1315Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: homework1337Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
OTIS Mock AIME98.3%91.1%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%68.8%Claude Opus 4.8
FrontierMath, tier 456.1%29.3%Claude Opus 4.8
ProofBench69.0%49.0%Claude Opus 4.8
LMArena Text: math14861495GLM 5.3
LMArena Text: mathematical work14971497Claude Opus 4.8
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index54
Knowledge benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
MMLU Pro89.6%86.8%Claude Opus 4.8
LegalBench (Vals AI)83.6%84.8%GLM 5.3
CorpFin (Vals AI)66.7%Not measuredOnly Claude Opus 4.8 measured
TaxEval (Vals AI)75.6%72.4%Claude Opus 4.8
MortgageTax (Vals AI)69.9%Not measuredOnly Claude Opus 4.8 measured
MedCode (Vals AI)53.2%42.9%Claude Opus 4.8
SimpleQA Verified53.0%41.0%Claude Opus 4.8
LMArena Text: science14771498GLM 5.3
LMArena Text: medicine and healthcare14641481GLM 5.3
LMArena Text: legal and government14771473Claude Opus 4.8
LMArena Text: business and finance14581459GLM 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 index27
Web design benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
Design Arena: websites12581295GLM 5.3
Design Arena: UI components12561314GLM 5.3
Design Arena: game dev12641311GLM 5.3
Design Arena: data viz12401260GLM 5.3
Design Arena: 3D12231332GLM 5.3
Design Arena: all code categories12551304GLM 5.3
Design Arena: SVG11941292GLM 5.3
Design Arena: ASCII art12761213Claude Opus 4.8
LiveBench design78.8%77.3%Claude Opus 4.8
GeneralLike-for-likePublic boards, shown as published, kept out of the index617
General benchmarks for Claude Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 5.3Leader
Vals IndexNot measured59.7%Only GLM 5.3 measured
LiveBench data analysis66.0%70.2%GLM 5.3
Public Benefits Bench (Vals AI)68.1%68.5%GLM 5.3
SAGE (Vals AI)54.8%Not measuredOnly Claude Opus 4.8 measured
MedScribe (Vals AI)85.8%88.8%GLM 5.3
Vals Multimodal Index70.9%Not measuredOnly Claude Opus 4.8 measured
IFBench62.2%Not measuredOnly Claude Opus 4.8 measured
Long context reasoning (AA-LCR)77.7%79.7%GLM 5.3
DTBench94.9%87.7%Claude Opus 4.8
LMCA57.5%55.5%Claude Opus 4.8
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
LMArena Text14611474GLM 5.3
LMArena Text: instruction following14761479GLM 5.3
LMArena Text: creative writing14541458GLM 5.3
LMArena Vision1294Not measuredOnly Claude Opus 4.8 measured
LMArena Text: English14681482GLM 5.3
LMArena Text: non-English14501459GLM 5.3
LMArena Text: Chinese15061532GLM 5.3
LMArena Text: German14721488GLM 5.3
LMArena Text: Japanese14421460GLM 5.3
LMArena Text: Korean14311460GLM 5.3
LMArena Text: French14811503GLM 5.3
LMArena Text: Spanish14651462Claude Opus 4.8
LMArena Text: Russian14741469Claude Opus 4.8
LMArena Text: Polish14591466GLM 5.3
LMArena Text: multi-turn14761472Claude Opus 4.8
LMArena Text: longer queries14831483Claude Opus 4.8
LMArena Text: writing and language14611469GLM 5.3
LMArena Text: entertainment and media14401447GLM 5.3
LMArena Vision: English1293Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: Chinese1346Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: reading text1303Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: humor1282Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: creative writing1301Not measuredOnly Claude Opus 4.8 measured
LMArena Document1475Not measuredOnly Claude Opus 4.8 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 Opus 4.8 and GLM 5.3
BenchmarkClaude Opus 4.8GLM 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 Opus 4.8$0.018Fits in one request
GLM 5.3$0.0008Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
GLM 5.3$0.0081Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits 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 Opus 4.8 and GLM 5.3
SpecificationAnthropic Claude Opus 4.8Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedMay 27, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.079
Output $/Mtok$25.00$1.40
Coding index66.073.1
Independent measurements behind it22
Cost per solved task$2.17$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than GLM 5.3 for coding?

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 66.0 for Claude Opus 4.8. Pick Claude Opus 4.8 when what matters is LiveCodeBench (Vals AI) or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Claude Opus 4.8 or GLM 5.3?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM 5.3 costs $0.079 and $1.40. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and GLM 5.3 $0.36.

Which has the bigger context window, Claude Opus 4.8 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.8 vs GLM 5.3 comparison based on?

91 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8'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-opus-4-8-vs-glm-5-3" title="Claude Opus 4.8 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-opus-4-8-vs-glm-5-3">LLMBenchmark.ai, Claude Opus 4.8 vs GLM 5.3</a></p>