Enter opens the highlighted result. Esc closes.

Claude Fable 5.2 vs GLM 5.3

Claude Fable 5.2 leads GLM 5.3 on coding, 87.8 to 68.5 on the Vibe Coding Index, and GLM 5.3 costs 9.1x less per output token ($4.40 vs $40.00 per million). Updated November 14, 2026; 46 benchmarks have a result for both.

Replace Claude Fable 5.2 Replace GLM 5.3
Claude Fable 5.2Anthropic
Coding
87.8
Overall
91.7
Output $/M
$40.00
43
GLM 5.3Z.ai
Coding
68.5
Overall
67.0
Output $/M
$4.40
3
vs boards won of 46 shared

Claude Fable 5.2 or GLM 5.3: which to pick

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 68.5 for GLM 5.3, though on 4 benchmarks against 5.

Pick GLM 5.3 for output tokens 9.1x cheaper ($4.40 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).

Model AClaude Fable 5.2Anthropic87.8/1004 independent benchmarksNo cost per solved taskModel BGLM 5.3Z.ai68.5/1005 independent benchmarks$0.36 per solved task
Shared results
46
Claude Fable 5.2 only
22
GLM 5.3 only
63
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 5.2 87.8 from 4 benchmarks, GLM 5.3 68.5 from 5 benchmarks.
Widest category
Knowledge, 41.7 points apart on average over 2 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Fable 5.2 100.0% against GLM 5.3 29.3%, 70.7 points apart on a 0 to 100 scale.
Output price
Claude Fable 5.2 $40.00 against GLM 5.3 $4.40 per million output tokens, 9.1x apart.
Context window
Claude Fable 5.2 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 Fable 5.2BarsGLM 5.3Ties
Coding130
Intelligence20
Agentic work33
Reasoning90
Math40
Knowledge20
Web design50
General50
All shared boards433
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
Coding benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
LiveBench coding79.2%Not measuredOnly Claude Fable 5.2 measured
LMArena WebDev18381622Claude Fable 5.2
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)65.2%38.9%Claude Fable 5.2
Vibe Code Bench (Vals AI)93.8%78.1%Claude Fable 5.2
Code migration (Vals AI)Not measured44.2%Only GLM 5.3 measured
ProgramBench (Vals AI)19.0%1.5%Claude Fable 5.2
IOI (Vals AI)Not measured68.4%Only GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)Not measured71.5%Only GLM 5.3 measured
SWE-bench Multimodal (Vals AI)62.3%Not measuredOnly Claude Fable 5.2 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)Not measured72.1%Only GLM 5.3 measured
SciCode67.7%59.0%Claude Fable 5.2
Terminal-Bench 4.0 (Artificial Analysis run)61.6%41.9%Claude Fable 5.2
FrontierCode 2.049.1%21.6%Claude Fable 5.2
FrontierCodeNot measured40.1%Only GLM 5.3 measured
FrontierSWE69.9%30.2%Claude Fable 5.2
WeirdMLNot measured75.4%Only GLM 5.3 measured
ALE-Bench2509.81317.4Claude Fable 5.2
LMArena Text: codingNot measured1499Only GLM 5.3 measured
LMArena Text: software and ITNot measured1495Only GLM 5.3 measured
LMArena WebDev: React19151642Claude Fable 5.2
LMArena WebDev: HTML17381596Claude Fable 5.2
SWE-Bench Pro V2Not measured95.6%Only GLM 5.3 measured
GameBench 299.172.3Claude Fable 5.2
Terminal-Bench 3.0Not measured32.4%Only GLM 5.3 measured
Terminal-Bench 4.0Not measured41.8%Only GLM 5.3 measured
CursorBench 4.060.0%42.6%Claude Fable 5.2
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
AA Intelligence Index64.631.7Claude Fable 5.2
Epoch Capabilities Index173.4157.1Claude Fable 5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index33
Agentic work benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
AA Agentic IndexNot measured53.1Only GLM 5.3 measured
Design Arena: agents building web appsNot measured1270Only GLM 5.3 measured
Design Arena: agents building full-stack apps1402Not measuredOnly Claude Fable 5.2 measured
Design Arena: agents building mobile apps13251184Claude Fable 5.2
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1217Only GLM 5.3 measured
Design Arena: spreadsheets1434Not measuredOnly Claude Fable 5.2 measured
LiveBench research94.5%Not measuredOnly Claude Fable 5.2 measured
LiveBench browser86.9%Not measuredOnly Claude Fable 5.2 measured
LiveBench long agentic82.9%Not measuredOnly Claude Fable 5.2 measured
SREBench (Vals AI)Not measured9.2%Only GLM 5.3 measured
Finance Agent (Vals AI)Not measured55.8%Only GLM 5.3 measured
Tax Agent Bench (Vals AI)32.1%43.3%GLM 5.3
Legal Research Bench (Vals AI)46.1%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)5.0%14.6%GLM 5.3
Excel Modeling Benchmark (Vals AI)Not measured56.3%Only GLM 5.3 measured
BioMysteryBench (Vals AI)83.7%Not measuredOnly Claude Fable 5.2 measured
Terminal-Bench-Science (Vals AI)55.7%5.7%Claude Fable 5.2
Vals Science Index63.7%Not measuredOnly Claude Fable 5.2 measured
APEX-Agents80.1%56.6%Claude Fable 5.2
Remote Labor Index41.3%Not measuredOnly Claude Fable 5.2 measured
PostTrainBenchNot measured34.5%Only GLM 5.3 measured
SpireClimb15.5%Not measuredOnly Claude Fable 5.2 measured
Vending-Bench 2Not measured$8,164Only GLM 5.3 measured
MCP AtlasNot measured84.2%Only GLM 5.3 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
GPQA DiamondNot measured88.1%Only GLM 5.3 measured
LiveBench reasoning88.8%Not measuredOnly Claude Fable 5.2 measured
MysteryMechanism (Vals AI)51.8%23.0%Claude Fable 5.2
GPQA Diamond (Artificial Analysis run)Not measured91.7%Only GLM 5.3 measured
Humanity's Last Exam (Artificial Analysis run)74.3%42.3%Claude Fable 5.2
HLE-Diamond (Artificial Analysis run)80.2%17.9%Claude Fable 5.2
CritPt v2, hard subset (Artificial Analysis run)76.5%33.5%Claude Fable 5.2
GPQA Diamond (Epoch AI run)93.9%90.9%Claude Fable 5.2
ARC-AGI98.5%Not measuredOnly Claude Fable 5.2 measured
ARC-AGI-293.8%Not measuredOnly Claude Fable 5.2 measured
SimpleBench94.9%66.2%Claude Fable 5.2
Chess puzzles79.0%37.0%Claude Fable 5.2
Mystery game puzzles90.0%33.0%Claude Fable 5.2
EBR-bench90.5%Not measuredOnly Claude Fable 5.2 measured
LMArena Text: hard promptsNot measured1493Only GLM 5.3 measured
LMArena Text: expertNot measured1519Only GLM 5.3 measured
LMArena Text: hard prompts in EnglishNot measured1500Only GLM 5.3 measured
Humanity's Last Exam (Scale run)72.4%16.4%Claude Fable 5.2
GoBench2566Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
OTIS Mock AIME99.7%91.1%Claude Fable 5.2
FrontierMath, tiers 1 to 395.1%68.8%Claude Fable 5.2
FrontierMath, tier 4100.0%29.3%Claude Fable 5.2
ProofBench100.0%49.0%Claude Fable 5.2
LMArena Text: mathNot measured1500Only GLM 5.3 measured
LMArena Text: mathematical workNot measured1502Only GLM 5.3 measured
MathArena82.8%Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
Knowledge benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 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)Not measured42.9%Only GLM 5.3 measured
AA-Omniscience66.86.0Claude Fable 5.2
SimpleQA Verified94.0%41.0%Claude Fable 5.2
LMArena Text: scienceNot measured1499Only GLM 5.3 measured
LMArena Text: medicine and healthcareNot measured1483Only GLM 5.3 measured
LMArena Text: legal and governmentNot measured1481Only GLM 5.3 measured
LMArena Text: business and financeNot measured1461Only GLM 5.3 measured
PRBench Finance47.1%Not measuredOnly Claude Fable 5.2 measured
PRBench Legal49.0%Not measuredOnly Claude Fable 5.2 measured
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
Design Arena: websites13511279Claude Fable 5.2
Design Arena: UI components13711284Claude Fable 5.2
Design Arena: game dev13961289Claude Fable 5.2
Design Arena: data vizNot measured1251Only GLM 5.3 measured
Design Arena: 3D15171295Claude Fable 5.2
Design Arena: all code categories13731284Claude Fable 5.2
Design Arena: SVGNot measured1246Only GLM 5.3 measured
Design Arena: ASCII artNot measured1208Only GLM 5.3 measured
LiveBench design85.1%Not measuredOnly Claude Fable 5.2 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index50
General benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 5.3Leader
Vals Index71.3%59.9%Claude Fable 5.2
LiveBench data analysis81.5%Not measuredOnly Claude Fable 5.2 measured
Public Benefits Bench (Vals AI)Not measured68.5%Only GLM 5.3 measured
MedScribe (Vals AI)Not measured88.8%Only GLM 5.3 measured
Long context reasoning (AA-LCR)83.3%79.7%Claude Fable 5.2
GDPval-AA18311655Claude Fable 5.2
DTBench99.2%87.7%Claude Fable 5.2
LMCA70.6%55.5%Claude Fable 5.2
Furniture assembly90.0%Not measuredOnly Claude Fable 5.2 measured
LMArena TextNot measured1475Only GLM 5.3 measured
LMArena Text: instruction followingNot measured1483Only GLM 5.3 measured
LMArena Text: creative writingNot measured1459Only GLM 5.3 measured
LMArena Text: EnglishNot measured1483Only GLM 5.3 measured
LMArena Text: non-EnglishNot measured1462Only GLM 5.3 measured
LMArena Text: ChineseNot measured1535Only GLM 5.3 measured
LMArena Text: GermanNot measured1497Only GLM 5.3 measured
LMArena Text: JapaneseNot measured1470Only GLM 5.3 measured
LMArena Text: KoreanNot measured1440Only GLM 5.3 measured
LMArena Text: FrenchNot measured1498Only GLM 5.3 measured
LMArena Text: SpanishNot measured1467Only GLM 5.3 measured
LMArena Text: RussianNot measured1472Only GLM 5.3 measured
LMArena Text: PolishNot measured1463Only GLM 5.3 measured
LMArena Text: multi-turnNot measured1474Only GLM 5.3 measured
LMArena Text: longer queriesNot measured1486Only GLM 5.3 measured
LMArena Text: writing and languageNot measured1468Only GLM 5.3 measured
LMArena Text: entertainment and mediaNot measured1447Only GLM 5.3 measured
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5.2 and GLM 5.3
BenchmarkClaude Fable 5.2GLM 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 Fable 5.2$0.028Fits in one request
GLM 5.3$0.0036Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5.2$0.520Fits in one request
GLM 5.3$0.083Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5.2$2.00Fits 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 Fable 5.2 and GLM 5.3
SpecificationAnthropic Claude Fable 5.2Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedNovember 9, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$8.00$1.40
Output $/Mtok$40.00$4.40
Coding index87.868.5
Independent measurements behind it45
Cost per solved taskNot computable$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5.2 better than GLM 5.3 for coding?

Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 68.5 for GLM 5.3, though on 4 benchmarks against 5. Pick GLM 5.3 for output tokens 9.1x cheaper ($4.40 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Fable 5.2 or GLM 5.3?

Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 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 Fable 5.2 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Fable 5.2 vs GLM 5.3 comparison based on?

46 benchmarks have a result for both models as of November 14, 2026. Claude Fable 5.2's coding index rests on 4 independent benchmarks and GLM 5.3's on 5. 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-5-2-vs-glm-5-3" title="Claude Fable 5.2 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-fable-5-2-vs-glm-5-3">LLMBenchmark.ai, Claude Fable 5.2 vs GLM 5.3</a></p>