BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.2 vs GLM 5.2

Full profiles: Claude Fable 5.2 (Anthropic) and GLM 5.2 (Zhipu AI): every benchmark, price and rank.

Updated · Data from 7 sources

As of 9 Nov 2026, Claude Fable 5.2 is ahead of GLM 5.2 on quality (69.4 vs 59.4 on the BenchLeader Index), but GLM 5.2 is 7.4× cheaper at $2.15 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.2 scores 69.4 on the BenchLeader Index and GLM 5.2 scores 59.4 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
  • GLM 5.2 costs $2.15 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 12 benchmarks both models have, Claude Fable 5.2 leads 11 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic GLM 5.2 benchmarks max Zhipu AIAdd a third model

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingClaude Fable 5.280 vs 62 category score; SciCode (AA) 67.7% vs 51.2%High
ReasoningClaude Fable 5.278 vs 57 category score; HLE-Diamond (AA) 80.2% vs 17.7%High
KnowledgeClaude Fable 5.282 vs 45 category score; AA-Omniscience v1.1 66.8 vs 0.6High
Long documentsClaude Fable 5.266 vs 64 category score; AA-LCR v1.1 83.3% vs 78.3%Medium
Chat quality (human preference)–Only GLM 5.2 has an Arena rating (67 category score)Not comparable
Lowest costGLM 5.2$2.15 vs $16.00 per 1M blended; agentic coding session $0.102 vs $0.640–
Fastest first answerClaude Fable 5.23.0 s (Claude Fable 5.2 (max)) vs 24.9 s (GLM 5.2 (max)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Fable 5.2 (max) leads on quality: 69.4 vs 59.4.
  • Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
  • GLM 5.2 (max) is stronger in agents & tools, human preference, instruction following, maths.
  • GLM 5.2 (max) is 7.4× cheaper ($2.15 vs $16.00 per 1M blended).

At a glance

SpecClaude Fable 5.2GLM 5.2
DeveloperAnthropicZhipu AI
Released9 Nov 202616 Jun 2026
Context window (tokens)1,000,0001,000,000
Compared atClaude Fable 5.2 (max)GLM 5.2 (max)
Open weightsNoYes
Price in / out / cached input per 1M$8.00 / $40.00 / $0.200$1.40 / $4.40 / $0.260

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryClaude Fable 5.2 (max)GLM 5.2 (max)Leader
Reasoning78.457.4Claude Fable 5.2
Coding80.262.1Claude Fable 5.2
Agents & tools–62.4not comparable
Maths–57.1not comparable
Knowledge81.744.5Claude Fable 5.2
Instruction following–71.8not comparable
Human preference–66.5not comparable
Long context66.463.8Claude Fable 5.2

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingKnowledgeLong contextClaude Fable 5.2, Reasoning: 78.4Claude Fable 5.2, Coding: 80.2Claude Fable 5.2, Knowledge: 81.7Claude Fable 5.2, Long context: 66.4GLM 5.2, Reasoning: 57.4GLM 5.2, Coding: 62.1GLM 5.2, Knowledge: 44.5GLM 5.2, Long context: 63.8

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Multimodal, Human preference.

ModelIndex

Where sources disagree

Across the 12 benchmarks both have, Claude Fable 5.2 leads 11, GLM 5.2 leads 1. Every overall index that rates both puts Claude Fable 5.2 ahead.

Overall indexClaude Fable 5.2 (max)GLM 5.2 (max)Leader
BenchLeader Index69.459.4Claude Fable 5.2

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureClaude Fable 5.2 (max)GLM 5.2 (max)
Blended price per 1M tokens$16.00$2.15
Input / output per 1M$8.00 / $40.00$1.40 / $4.40
Cached input per 1M$0.200$0.260
Price per task: chat reply$0.015$0.0019
Price per task: summarize a 30-page report$0.120$0.019
Price per task: code edit$0.108$0.015
Price per task: agentic coding session$0.640$0.102
Price per task: structured extraction$0.024$0.0037
Agentic coding session, input mostly cached$0.289$0.050
Cost per benchmark task (AA Index)$26.54–
Output tokens per task (AA Index)274k–
Of which reasoning193k–
Output speed72 tok/s84 tok/s
Time to first answer3.0 s24.9 s
Time to a complete answer–58.2 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.2 (max) scores 69.4 and takes 3 s to its first answer token; Claude Fable 5.2 (high) scores 68.9 in 3 s, Claude Fable 5.2 (xhigh) scores 68.7 in 3 s. GLM 5.2 (max) scores 59.4 and takes 25 s to its first answer token; GLM 5.2 scores 51.5 in 1 s, GLM 5.2 (no reasoning) scores 45.9 in 2 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

137 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherClaude Fable 5.2 (max)GLM 5.2 (max)
BenchLeader IndexBenchLeader69.459.4
Coding scoreBenchLeader80.262.1
Knowledge scoreBenchLeader81.744.5
Long context scoreBenchLeader66.463.8
Reasoning scoreBenchLeader78.457.4
Agents & tools scoreBenchLeader–62.4
Human preference scoreBenchLeader–66.5
Instruction following scoreBenchLeader–71.8
Maths scoreBenchLeader–57.1
Blended price $/MBenchLeader$16.00$2.15
Output speedBenchLeader72 tok/s84 tok/s
Time to first answerBenchLeader3.0 s24.9 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–91.9%
SimpleBenchSimpleBench–58.8%†
Arena Hard PromptsArena (LMArena)–1496
LiveBench 2.0 ReasoningLiveBench88.8%†–
LiveBench 1.0 ReasoningLiveBench–78.6%†
GPQA Diamond (AA)Artificial Analysis–89.5%
Humanity's Last Exam (AA)Artificial Analysis74.3%41.1%
HLE-Diamond (AA)Artificial Analysis80.2%17.7%
GPQA Diamond (Vals)Vals AI–85.6%†
Kagi LLM BenchmarkKagi LLM Benchmark–62.6%†
ARC-AGI-1ARC Prize97.5%77.0%†
ARC-AGI-2ARC Prize92.5%22.8%†
ARC-AGI-3ARC Prize94.9%–
CritPtArtificial Analysis35.4%20.9%
CritPt v2 hard subset (AA)Artificial Analysis76.5%–
MysteryMechanismVals AI51.8%†–
Chess PuzzlesEpoch AI Benchmarking Hub–22.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–18.0%†
LMCAEpoch AI Benchmarking Hub–45.8%
DTBenchEpoch AI Benchmarking Hub–93.6%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–78.7%
SciCodeSciCode–51.2%
WeirdMLWeirdML–70.1%
FrontierCodeCognition–24.5%†
Arena CodingArena (LMArena)–1515
Show all 137 benchmarks
MetricPublisherClaude Fable 5.2 (max)GLM 5.2 (max)
Coding
Arena WebDevArena (LMArena)–1608
LiveBench 2.0 CodingLiveBench79.2%†–
LiveBench 1.0 CodingLiveBench–79.7%†
SciCode (AA)Artificial Analysis67.7%51.2%
LiveCodeBenchVals AI–69.5%†
SWE-bench (Vals)Vals AI–82.8%
Code MigrationVals AI–37.9%
Code Migration v1.1Vals AI83.3%†–
ProgramBenchVals AI19.0%†0.5%
SWE-bench MultimodalVals AI62.3%†–
Vibe Code Bench v1.1Vals AI93.8%†64.0%
SWE Atlas: Codebase QnAScale AI SEAL–48.1%†
SWE Atlas: RefactoringScale AI SEAL–42.4%†
SWE Atlas: Test WritingScale AI SEAL–41.5%†
Surface Evolver BenchEpoch AI Benchmarking Hub–55.6%†
DeepSWE v1.1Epoch AI Benchmarking Hub–43.8%
ALE-BenchEpoch AI Benchmarking Hub–1010.2
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%1.0%
Terminal-Bench 2.1 (AA)Artificial Analysis–77.9%
Startrise FrontendStartrise–72.1%†
GameBench 2 OverallDuelLab GameBench 2–43.2†
GameBench 2 by reasoning settingDuelLab GameBench 2–32.9†
Design Arena WebsiteDesign Arena–1281†
FrontierCode 1.1 (AA)Artificial Analysis56.2%–
FrontierCode 2.0 (AA)Artificial Analysis48.8%–
Agents & tools
APEX-AgentsMercor–45.2%†
Arena AgentArena (LMArena)–0.4
LiveBench Long AgenticLiveBench82.9%†–
LiveBench BrowserLiveBench86.9%†–
LiveBench Agentic CodingLiveBench–51.8%†
Terminal-Bench HardArtificial Analysis–50.8%
τ²-Bench Telecom (AA)Artificial Analysis–99.1%
Terminal-Bench 2.1 (Vals)Vals AI–67.8%
MCP AtlasScale AI SEAL–77.8%†
HiL-BenchScale AI SEAL–43.7%†
τ³-bench Bankingτ²-bench–37.1%†
GDPval-AA v2.1Artificial Analysis1831–
τ³-Banking (AA)Artificial Analysis–34.6%
ITBench SRE (AA)Artificial Analysis–42.7%
APEX-Agents (AA)Artificial Analysis–33.7%
Finance Agent v2Vals AI–49.7%†
Finance Agent v2.1Vals AI69.5%†–
Harvey's Legal Agent Benchmark v1.1Vals AI5.0%†–
Harvey's Legal Agent Benchmark v1Vals AI–7.1%
Legal Research BenchVals AI46.1%†31.3%
SkillsBenchVals AI–45.1%
SREBenchVals AI–0.0%
Tax Agent BenchVals AI32.1%†–
Terminal-Bench 4.0 (Vals)Vals AI65.2%†–
Terminal-Bench ScienceVals AI55.7%†–
PostTrainBenchEpoch AI Benchmarking Hub–31.7%
GBAEvalEpoch AI Benchmarking Hub–0.0%†
Vending-Bench 2Andon Labs–8313.8†
AutomationBenchArtificial Analysis76.4%28.4%
GDP.pdf (AA)Artificial Analysis24.2%10.4%
Harvey LAB-AA v1.1Harvey7.2%–
EnterpriseOps-GymArtificial Analysis–42.7%
AA-Briefcase v1.1Artificial Analysis17851226
Design Arena AgenticDesign Arena–1190†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis73.3%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–59.2%
FrontierMath Tier 4Epoch AI Benchmarking Hub–29.3%
OTIS Mock AIMEEpoch AI Benchmarking Hub–86.4%
ProofBenchVals AI–35.0%
LiveBench MathematicsLiveBench–89.8%†
AIME 2026MathArena–90.0%†
HMMT February 2026MathArena–92.4%†
MathArena ApexMathArena–19.8%†
Arena MathsArena (LMArena)–1487
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–34.2%
LiveBench 2.0 Data AnalysisLiveBench81.5%†–
LiveBench ResearchLiveBench94.5%†–
LiveBench 1.0 Data AnalysisLiveBench–73.7%†
AA-Omniscience v1.1Artificial Analysis66.80.6
MMLU-ProVals AI–86.7%†
LegalBenchVals AI–84.1%†
CorpFinVals AI–66.1%†
TaxEvalVals AI–73.3%†
BioMysteryBenchVals AI83.7%†–
Excel Modeling BenchmarkVals AI–61.5%†
Excel Modeling Benchmark v1.1Vals AI77.4%†–
MedCodeVals AI–40.8%†
MedScribeVals AI–83.5%†
DrugDiscoveryBenchScale AI SEAL–36.2%†
EBR-benchEpoch AI Benchmarking Hub–9.5%
AA-Omniscience v1.1: accuracyArtificial Analysis79.1%21.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.7%74.1%
HealthBench Professional (AA)OpenAI67.7%–
Instruction following
LiveBench LanguageLiveBench–76.2%†
LiveBench Instruction FollowingLiveBench–62.3%†
IFBenchArtificial Analysis–73.3%
Arena Instruction FollowingArena (LMArena)–1470
Human preference
Arena TextArena (LMArena)–1475
EQ-Bench 4EQ-Bench–1208†
Arena Creative WritingArena (LMArena)–1451
Arena Multi-turnArena (LMArena)–1476
Arena Longer QueriesArena (LMArena)–1486
Multimodal
LiveBench DesignLiveBench85.1%†–
AA-3DArtificial Analysis1271–
Long context
AA-LCR v1.1Artificial Analysis83.3%78.3%
MLCRArtificial Analysis–12.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–153.0†
LiveBench 2.0LiveBench84.9%†–
LiveBench 1.0LiveBench–73.2%†
AA Intelligence Index v5.0Artificial Analysis64.6–
AA Intelligence Index v4.3.2Artificial Analysis–33.7
AA Progress Index v1Artificial Analysis–302.5
Vals IndexVals AI71.3†–
Vals Finance IndexVals AI63.6%†–
Vals Science IndexVals AI63.7%†–
Safety & honesty
FORTRESSScale AI SEAL–48.7%†
Metadata
AA Openness IndexArtificial Analysis–44.4

Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GLM 5.2 (max): BenchLeader Index 60.2 → 59.5.
  • GLM 5.2 (max): 4 new results (HLE-Diamond (AA), AA-Omniscience v1.1, AA-Omniscience v1.1: accuracy…).
  • GLM 5.2 (max): cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.2 (max): 1 score revision; cached input price moved from $0.26/M to $0.30/M (15% up).
  • GLM 5.2 (max): cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.2 (max): cached input price moved from $0.26/M to $0.30/M (15% up).
  • GLM 5.2 (max): BenchLeader Index 61.3 → 60.2.
  • GLM 5.2 (max): 1 new result (AA Progress Index v1); cached input price moved from $0.30/M to $0.26/M (13% down).
  • GLM 5.2 (max): BenchLeader Index 61.8 → 61.3.
  • GLM 5.2 (max): cached input price moved from $0.26/M to $0.30/M (15% up).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Claude Fable 5.2 vs GLM 5.2: questions

Is Claude Fable 5.2 better than GLM 5.2?
Claude Fable 5.2 (max) leads on quality: 69.4 vs 59.4. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.2 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
Claude Fable 5.2 vs GLM 5.2: which is cheaper, and will that change?
GLM 5.2 is cheaper today: $2.15 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Fable 5.2 or GLM 5.2 better for coding?
Claude Fable 5.2 scores higher in coding (80 vs 62 on the category index, where 50 is average).
Which is faster, Claude Fable 5.2 or GLM 5.2?
GLM 5.2 streams faster (84 vs 72 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Claude Fable 5.2 scores higher on long-context benchmarks (66 vs 64). Both accept 1,000,000 tokens of context.
More questions (3)
Which has lower latency?
Claude Fable 5.2 answers first: 3.0 s against 24.9 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Claude Fable 5.2 vs GLM 5.2?
Across the 12 benchmarks both have, Claude Fable 5.2 leads 11, GLM 5.2 leads 1. Every overall index that rates both puts Claude Fable 5.2 ahead.
When was Claude Fable 5.2 released?
Claude Fable 5.2 was released on 9 Nov 2026.