Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs GLM 5.2

Claude Fable 5 leads GLM 5.2 on coding, 79.3 to 61.1 on the Vibe Coding Index, and GLM 5.2 costs 11.4x less per output token ($4.40 vs $50.00 per million). Updated October 21, 2026; 96 benchmarks have a result for both.

Replace Claude Fable 5 Replace GLM 5.2
Claude Fable 5Anthropic
Coding
79.3
Overall
79.0
Output $/M
$50.00
92
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
4
vs boards won of 96 shared

Claude Fable 5 or GLM 5.2: which to pick

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 61.1 for GLM 5.2.

Pick GLM 5.2 for output tokens 11.4x cheaper ($4.40 vs $50.00 per million) and a lower cost per solved task ($0.86 against $2.16).

Model AClaude Fable 5Anthropic79.3/1006 independent benchmarks$2.16 per solved taskModel BGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved task
Shared results
96
Claude Fable 5 only
31
GLM 5.2 only
2
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 Fable 5 79.3 from 6 benchmarks, GLM 5.2 61.1 from 4 benchmarks.
Widest category
Math, 28.7 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Fable 5 89.2% against GLM 5.2 22.8%, 66.4 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against GLM 5.2 $4.40 per million output tokens, 11.4x apart.
Context window
Claude Fable 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 Fable 5BarsGLM 5.2Ties
Coding170
Intelligence20
Agentic work142
Reasoning131
Math60
Knowledge100
Web design80
General221
All shared boards924
CodingLike-for-likeSix of these boards feed the Vibe Coding Index170
Coding benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
LiveBench coding98.3%Not measuredOnly Claude Fable 5 measured
LMArena WebDev16241604Claude Fable 5
AA Coding Index76.568.8Claude Fable 5
LiveCodeBench (Vals AI)89.8%69.5%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%82.8%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%Not measuredOnly Claude Fable 5 measured
Vibe Code Bench (Vals AI)90.3%64.0%Claude Fable 5
Code migration (Vals AI)55.1%37.9%Claude Fable 5
ProgramBench (Vals AI)2.0%0.5%Claude Fable 5
Terminal-Bench 2.1 (Vals AI)80.5%67.8%Claude Fable 5
SkillsBench (Vals AI)Not measured45.1%Only GLM 5.2 measured
SciCode61.0%51.2%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%50.8%Claude Fable 5
FrontierCode53.5%24.5%Claude Fable 5
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%Not measuredOnly Claude Fable 5 measured
WeirdML91.9%70.1%Claude Fable 5
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.31047.0Claude Fable 5
LMArena Text: coding15181487Claude Fable 5
LMArena Text: software and IT15131486Claude Fable 5
LMArena WebDev: React16311617Claude Fable 5
LMArena WebDev: HTML16511565Claude Fable 5
LMArena WebDev: from an image1623Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
AA Intelligence Index49.633.7Claude Fable 5
Epoch Capabilities Index163.4151.9Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index142
Agentic work benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
AA Agentic Index50.738.4Claude Fable 5
Design Arena: agents building web apps12611222Claude Fable 5
Design Arena: agents building full-stack apps12801241Claude Fable 5
Design Arena: agents building mobile apps12641160Claude Fable 5
Design Arena: agents building Android apps12831178Claude Fable 5
Design Arena: agents building Godot games12921142Claude Fable 5
Design Arena: agents building games12851206Claude Fable 5
Design Arena: HTML slides12771175Claude Fable 5
Design Arena: PowerPoint slides12951195Claude Fable 5
LiveBench research86.9%Not measuredOnly Claude Fable 5 measured
LiveBench browser92.0%Not measuredOnly Claude Fable 5 measured
LiveBench long agentic53.2%Not measuredOnly Claude Fable 5 measured
SREBench (Vals AI)Not measured0.0%Only GLM 5.2 measured
Finance Agent (Vals AI)56.3%49.7%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%Not measuredOnly Claude Fable 5 measured
Legal Research Bench (Vals AI)49.5%31.3%Claude Fable 5
Excel Modeling Benchmark (Vals AI)73.7%61.5%Claude Fable 5
Terminal-Bench-Science (Vals AI)15.7%Not measuredOnly Claude Fable 5 measured
τ²-Bench Telecom98.5%99.1%GLM 5.2
APEX-Agents63.6%45.2%Claude Fable 5
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
PostTrainBench41.8%31.7%Claude Fable 5
Vending-Bench 2$5,680$8,314GLM 5.2
LMArena Search1229Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
GPQA Diamond93.2%85.6%Claude Fable 5
LiveBench reasoning89.7%Not measuredOnly Claude Fable 5 measured
MMMU Pro (Vals AI)89.3%Not measuredOnly Claude Fable 5 measured
GPQA Diamond (Artificial Analysis run)92.6%89.5%Claude Fable 5
Humanity's Last Exam (Artificial Analysis run)55.5%41.1%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%91.9%GLM 5.2
ARC-AGI98.5%77.0%Claude Fable 5
ARC-AGI-289.2%22.8%Claude Fable 5
SimpleBench81.9%58.8%Claude Fable 5
Chess puzzles47.0%22.0%Claude Fable 5
Mystery game puzzles52.0%19.0%Claude Fable 5
EBR-bench39.5%9.5%Claude Fable 5
LMArena Text: hard prompts15071481Claude Fable 5
LMArena Text: expert15341487Claude Fable 5
LMArena Text: hard prompts in English15091481Claude Fable 5
LMArena Vision: diagrams1357Not measuredOnly Claude Fable 5 measured
LMArena Vision: homework1361Not measuredOnly Claude Fable 5 measured
Kagi LLM Benchmark91.4%62.6%Claude Fable 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
OTIS Mock AIME100.0%86.4%Claude Fable 5
FrontierMath, tiers 1 to 387.0%59.2%Claude Fable 5
FrontierMath, tier 490.2%29.3%Claude Fable 5
ProofBench95.0%35.0%Claude Fable 5
LMArena Text: math15161483Claude Fable 5
LMArena Text: mathematical work15151489Claude Fable 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 Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
MMLU Pro91.5%86.7%Claude Fable 5
LegalBench (Vals AI)88.6%84.1%Claude Fable 5
CorpFin (Vals AI)71.8%66.1%Claude Fable 5
TaxEval (Vals AI)76.9%73.3%Claude Fable 5
MortgageTax (Vals AI)68.9%Not measuredOnly Claude Fable 5 measured
MedCode (Vals AI)56.1%40.8%Claude Fable 5
SimpleQA Verified70.7%34.2%Claude Fable 5
LMArena Text: science15061489Claude Fable 5
LMArena Text: medicine and healthcare14801475Claude Fable 5
LMArena Text: legal and government14981486Claude Fable 5
LMArena Text: business and finance14801451Claude Fable 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 Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
Design Arena: websites12961285Claude Fable 5
Design Arena: UI components13191296Claude Fable 5
Design Arena: game dev13351268Claude Fable 5
Design Arena: data viz13041285Claude Fable 5
Design Arena: 3D13191288Claude Fable 5
Design Arena: all code categories13101288Claude Fable 5
Design Arena: SVG13021214Claude Fable 5
Design Arena: ASCII art13291190Claude Fable 5
LiveBench design84.7%Not measuredOnly Claude Fable 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index221
General benchmarks for Claude Fable 5 and GLM 5.2
BenchmarkClaude Fable 5GLM 5.2Leader
LiveBench data analysis80.5%Not measuredOnly Claude Fable 5 measured
Public Benefits Bench (Vals AI)70.4%Not measuredOnly Claude Fable 5 measured
SAGE (Vals AI)51.9%Not measuredOnly Claude Fable 5 measured
MedScribe (Vals AI)88.5%83.5%Claude Fable 5
Vals Multimodal Index74.2%Not measuredOnly Claude Fable 5 measured
IFBench63.5%73.3%GLM 5.2
Long context reasoning (AA-LCR)82.3%78.3%Claude Fable 5
DTBench98.4%93.6%Claude Fable 5
LMCA61.2%45.8%Claude Fable 5
Surface Evolver Bench95.0%55.6%Claude Fable 5
Furniture assembly35.8%Not measuredOnly Claude Fable 5 measured
LMArena Text14911470Claude Fable 5
LMArena Text: instruction following15021466Claude Fable 5
LMArena Text: creative writing14941463Claude Fable 5
LMArena Vision1325Not measuredOnly Claude Fable 5 measured
LMArena Text: English14981475Claude Fable 5
LMArena Text: non-English14821459Claude Fable 5
LMArena Text: Chinese15431522Claude Fable 5
LMArena Text: German14861470Claude Fable 5
LMArena Text: Japanese15041450Claude Fable 5
LMArena Text: Korean14871440Claude Fable 5
LMArena Text: French15051479Claude Fable 5
LMArena Text: Spanish14981478Claude Fable 5
LMArena Text: Russian15031468Claude Fable 5
LMArena Text: Polish14941456Claude Fable 5
LMArena Text: multi-turn15041469Claude Fable 5
LMArena Text: longer queries15101480Claude Fable 5
LMArena Text: writing and language15011463Claude Fable 5
LMArena Text: entertainment and media14821450Claude Fable 5
LMArena Vision: English1323Not measuredOnly Claude Fable 5 measured
LMArena Vision: Chinese1373Not measuredOnly Claude Fable 5 measured
LMArena Vision: reading text1337Not measuredOnly Claude Fable 5 measured
LMArena Vision: humor1341Not measuredOnly Claude Fable 5 measured
LMArena Vision: creative writing1338Not measuredOnly Claude Fable 5 measured
LMArena Document1496Not measuredOnly Claude Fable 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 Fable 5 and GLM 5.2
BenchmarkClaude Fable 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 Fable 5$0.035Fits in one request
GLM 5.2$0.0036Fits in one request

GLM 5.2 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
GLM 5.2$0.083Fits in one request

GLM 5.2 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits 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 Fable 5 and GLM 5.2
SpecificationAnthropic Claude Fable 5Z.ai GLM 5.2
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedJune 9, 2026June 16, 2026
Context window1M1.05M
Input $/Mtok$10.00$1.40
Output $/Mtok$50.00$4.40
Coding index79.361.1
Independent measurements behind it64
Cost per solved task$2.16$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than GLM 5.2 for coding?

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 61.1 for GLM 5.2. Pick GLM 5.2 for output tokens 11.4x cheaper ($4.40 vs $50.00 per million) and a lower cost per solved task ($0.86 against $2.16).

Which is cheaper, Claude Fable 5 or GLM 5.2?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and GLM 5.2 $0.86.

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

GLM 5.2, with 1.05M tokens against 1M.

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

96 benchmarks have a result for both models as of October 21, 2026. Claude Fable 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-fable-5-vs-glm-5-2" title="Claude Fable 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-fable-5-vs-glm-5-2">LLMBenchmark.ai, Claude Fable 5 vs GLM 5.2</a></p>