Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs GLM 5.2

Claude Opus 5 leads GLM 5.2 on coding, 83.0 to 61.1 on the Vibe Coding Index, and GLM 5.2 costs 5.7x less per output token ($4.40 vs $25.00 per million). Updated October 22, 2026; 92 benchmarks have a result for both.

Replace Claude Opus 5 Replace GLM 5.2
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
92
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
0
vs boards won of 92 shared

Claude Opus 5 or GLM 5.2: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 61.1 for GLM 5.2.

Pick GLM 5.2 for output tokens 5.7x cheaper ($4.40 vs $25.00 per million) and a lower cost per solved task ($0.86 against $1.33).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved task
Shared results
92
Claude Opus 5 only
39
GLM 5.2 only
6
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 Opus 5 83.0 from 6 benchmarks, GLM 5.2 61.1 from 4 benchmarks.
Widest category
Math, 27.4 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 5 90.4% against GLM 5.2 22.8%, 67.6 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against GLM 5.2 $4.40 per million output tokens, 5.7x apart.
Context window
Claude Opus 5 takes 1M tokens, GLM 5.2 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 5BarsGLM 5.2Ties
Coding170
Intelligence20
Agentic work150
Reasoning130
Math60
Knowledge100
Web design80
General210
All shared boards920
CodingLike-for-likeSix of these boards feed the Vibe Coding Index170
Coding benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
LiveBench coding90.8%Not measuredOnly Claude Opus 5 measured
LMArena WebDev16891604Claude Opus 5
AA Coding Index78.068.8Claude Opus 5
LiveCodeBench (Vals AI)89.0%69.5%Claude Opus 5
SWE-bench Verified (Vals AI)97.0%82.8%Claude Opus 5
Terminal-Bench 4 (Vals AI)53.5%Not measuredOnly Claude Opus 5 measured
Vibe Code Bench (Vals AI)88.4%64.0%Claude Opus 5
Code migration (Vals AI)57.5%37.9%Claude Opus 5
ProgramBench (Vals AI)3.0%0.5%Claude Opus 5
IOI (Vals AI)84.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench 2.1 (Vals AI)84.6%67.8%Claude Opus 5
Vibe Code Bench 1-100 (Vals AI)28.5%Not measuredOnly Claude Opus 5 measured
SkillsBench (Vals AI)60.4%45.1%Claude Opus 5
CyberBench (Vals AI)65.4%Not measuredOnly Claude Opus 5 measured
SciCode56.4%51.2%Claude Opus 5
Terminal-Bench Hard (Artificial Analysis run)Not measured50.8%Only GLM 5.2 measured
FrontierCode53.4%24.5%Claude Opus 5
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
WeirdML91.8%70.1%Claude Opus 5
ALE-Bench2164.61047.0Claude Opus 5
LMArena Text: coding15331487Claude Opus 5
LMArena Text: software and IT15271486Claude Opus 5
LMArena WebDev: React17111617Claude Opus 5
LMArena WebDev: HTML16801565Claude Opus 5
LMArena WebDev: from an image1662Not measuredOnly Claude Opus 5 measured
SciCode13.8%Not measuredOnly Claude Opus 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 Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
AA Intelligence Index50.833.7Claude Opus 5
Epoch Capabilities Index163.9151.9Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index150
Agentic work benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
AA Agentic Index56.538.4Claude Opus 5
Design Arena: agents building web apps12661222Claude Opus 5
Design Arena: agents building full-stack apps13061241Claude Opus 5
Design Arena: agents building mobile apps13481159Claude Opus 5
Design Arena: agents building Android apps12571178Claude Opus 5
Design Arena: agents building Godot games12791142Claude Opus 5
Design Arena: agents building games12611206Claude Opus 5
Design Arena: HTML slidesNot measured1125Only GLM 5.2 measured
Design Arena: PowerPoint slides12401170Claude Opus 5
LiveBench research88.9%Not measuredOnly Claude Opus 5 measured
LiveBench browser84.0%Not measuredOnly Claude Opus 5 measured
LiveBench long agentic62.1%Not measuredOnly Claude Opus 5 measured
SREBench (Vals AI)12.2%0.0%Claude Opus 5
Finance Agent (Vals AI)58.6%49.7%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%Not measuredOnly Claude Opus 5 measured
Legal Research Bench (Vals AI)55.3%31.3%Claude Opus 5
Excel Modeling Benchmark (Vals AI)73.6%61.5%Claude Opus 5
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)27.1%Not measuredOnly Claude Opus 5 measured
Vals Science Index47.9%Not measuredOnly Claude Opus 5 measured
Time Horizon Index (Vals AI)18.8%Not measuredOnly Claude Opus 5 measured
CUA-bench (Vals AI)9.0%Not measuredOnly Claude Opus 5 measured
τ²-Bench TelecomNot measured99.1%Only GLM 5.2 measured
APEX-Agents65.8%45.2%Claude Opus 5
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%Not measuredOnly Claude Opus 5 measured
PostTrainBench35.0%31.7%Claude Opus 5
Vending-Bench 2$11,182$8,314Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
GPQA Diamond93.4%85.6%Claude Opus 5
LiveBench reasoning91.2%Not measuredOnly Claude Opus 5 measured
MysteryMechanism (Vals AI)37.4%Not measuredOnly Claude Opus 5 measured
MMMU Pro (Vals AI)89.9%Not measuredOnly Claude Opus 5 measured
GPQA Diamond (Artificial Analysis run)93.7%89.5%Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)54.9%41.1%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%91.9%Claude Opus 5
ARC-AGI97.5%77.0%Claude Opus 5
ARC-AGI-290.4%22.8%Claude Opus 5
SimpleBench80.6%58.8%Claude Opus 5
Chess puzzles43.0%22.0%Claude Opus 5
Mystery game puzzles59.0%19.0%Claude Opus 5
EBR-bench45.7%9.5%Claude Opus 5
LMArena Text: hard prompts15271481Claude Opus 5
LMArena Text: expert15541487Claude Opus 5
LMArena Text: hard prompts in English15231481Claude Opus 5
LMArena Vision: diagrams1348Not measuredOnly Claude Opus 5 measured
LMArena Vision: homework1338Not measuredOnly Claude Opus 5 measured
Kagi LLM BenchmarkNot measured62.6%Only GLM 5.2 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
OTIS Mock AIME98.9%86.4%Claude Opus 5
FrontierMath, tiers 1 to 385.6%59.2%Claude Opus 5
FrontierMath, tier 473.2%29.3%Claude Opus 5
ProofBench99.0%35.0%Claude Opus 5
LMArena Text: math15331483Claude Opus 5
LMArena Text: mathematical work15441489Claude Opus 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
MMLU Pro91.6%86.7%Claude Opus 5
LegalBench (Vals AI)87.0%84.1%Claude Opus 5
CorpFin (Vals AI)73.2%66.1%Claude Opus 5
TaxEval (Vals AI)75.1%73.3%Claude Opus 5
MortgageTax (Vals AI)72.1%Not measuredOnly Claude Opus 5 measured
MedCode (Vals AI)63.6%40.8%Claude Opus 5
SimpleQA Verified59.9%34.2%Claude Opus 5
LMArena Text: science15311489Claude Opus 5
LMArena Text: medicine and healthcare15251475Claude Opus 5
LMArena Text: legal and government15301486Claude Opus 5
LMArena Text: business and finance15011451Claude Opus 5
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
Design Arena: websites13091285Claude Opus 5
Design Arena: UI components13461294Claude Opus 5
Design Arena: game dev13371268Claude Opus 5
Design Arena: data viz13291285Claude Opus 5
Design Arena: 3D13341287Claude Opus 5
Design Arena: all code categories13231287Claude Opus 5
Design Arena: SVG13111213Claude Opus 5
Design Arena: ASCII art13521191Claude Opus 5
LiveBench design83.0%Not measuredOnly Claude Opus 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
General benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
LiveBench data analysis74.6%Not measuredOnly Claude Opus 5 measured
Public Benefits Bench (Vals AI)76.9%Not measuredOnly Claude Opus 5 measured
SAGE (Vals AI)49.4%Not measuredOnly Claude Opus 5 measured
MedScribe (Vals AI)91.0%83.5%Claude Opus 5
Vals Multimodal Index73.9%Not measuredOnly Claude Opus 5 measured
IFBenchNot measured73.3%Only GLM 5.2 measured
Long context reasoning (AA-LCR)82.0%78.3%Claude Opus 5
DTBench97.9%93.6%Claude Opus 5
LMCA64.5%45.8%Claude Opus 5
Surface Evolver BenchNot measured55.6%Only GLM 5.2 measured
Furniture assembly60.8%Not measuredOnly Claude Opus 5 measured
LMArena Text15091470Claude Opus 5
LMArena Text: instruction following15181466Claude Opus 5
LMArena Text: creative writing14931463Claude Opus 5
LMArena Vision1320Not measuredOnly Claude Opus 5 measured
LMArena Text: English15081475Claude Opus 5
LMArena Text: non-English15021459Claude Opus 5
LMArena Text: Chinese15731522Claude Opus 5
LMArena Text: German15271470Claude Opus 5
LMArena Text: Japanese15201450Claude Opus 5
LMArena Text: Korean15171440Claude Opus 5
LMArena Text: French15191479Claude Opus 5
LMArena Text: Spanish15231478Claude Opus 5
LMArena Text: Russian15071468Claude Opus 5
LMArena Text: Polish15221456Claude Opus 5
LMArena Text: multi-turn15001469Claude Opus 5
LMArena Text: longer queries15171480Claude Opus 5
LMArena Text: writing and language14991463Claude Opus 5
LMArena Text: entertainment and media14811450Claude Opus 5
LMArena Vision: English1315Not measuredOnly Claude Opus 5 measured
LMArena Vision: Chinese1400Not measuredOnly Claude Opus 5 measured
LMArena Vision: reading text1329Not measuredOnly Claude Opus 5 measured
LMArena Vision: humor1293Not measuredOnly Claude Opus 5 measured
LMArena Vision: creative writing1313Not measuredOnly Claude Opus 5 measured
LMArena Document1516Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 5 and GLM 5.2
BenchmarkClaude Opus 5GLM 5.2Leader
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 5$0.018Fits in one request
GLM 5.2$0.0036Fits in one request

GLM 5.2 costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request
GLM 5.2$0.083Fits in one request

GLM 5.2 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits in one request
GLM 5.2$0.324Fits in one request

GLM 5.2 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 5 and GLM 5.2
SpecificationAnthropic Claude Opus 5Z.ai GLM 5.2
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedJuly 24, 2026June 16, 2026
Context window1M1.05M
Input $/Mtok$5.00$1.40
Output $/Mtok$25.00$4.40
Coding index83.061.1
Independent measurements behind it64
Cost per solved task$1.33$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than GLM 5.2 for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 61.1 for GLM 5.2. Pick GLM 5.2 for output tokens 5.7x cheaper ($4.40 vs $25.00 per million) and a lower cost per solved task ($0.86 against $1.33).

Which is cheaper, Claude Opus 5 or GLM 5.2?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and GLM 5.2 $0.86.

Which has the bigger context window, Claude Opus 5 or GLM 5.2?

GLM 5.2, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 5 vs GLM 5.2 comparison based on?

92 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5's coding index rests on 6 independent benchmarks and GLM 5.2's on 4. 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-5-vs-glm-5-2" title="Claude Opus 5 vs GLM 5.2, 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-5-vs-glm-5-2">LLMBenchmark.ai, Claude Opus 5 vs GLM 5.2</a></p>