Skip to main content
BenchLM
Advertise

Model comparison

Claude Fable 5 vs GLM-5.2

Data verified

Head-to-head evidence from 27 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

83.68/100
Margin
19.7pts
← winning
63.96/100
2 category wins0 category wins

Public leaderboard positions: Claude Fable 5 #2 (Supported); GLM-5.2 #37 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Fable 5 and GLM-5.2 share 27 comparable benchmark results. 2 of 8 categories are comparable. 7 results are unique to Claude Fable 5; 16 to GLM-5.2.

Updated July 23, 2026
Shared results
27
Claude Fable 5 only
7
GLM-5.2 only
16
Comparable categories
2 / 8

Pick Claude Fable 5 if you want the stronger benchmark profile. GLM-5.2 only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 27 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Fable 5 is clearly ahead on the BenchAlign aggregate, 83.68 to 63.96. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Fable 5's sharpest advantage is in coding, where it averages 89.2 against 62.1. The single biggest benchmark swing on the page is SWE-bench Pro, 80% to 62.1%.

Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $1.40 input / $4.40 output per 1M tokens for GLM-5.2. That is roughly 11.4x on output cost alone. Claude Fable 5 gives you the larger context window at 1M+, compared with 1M for GLM-5.2.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Fable 5 and GLM-5.2
CategoryClaude Fable 5ΔGLM-5.2
CodingClaude Fable 589.2Margin← 27.1GLM-5.262.1
AgenticClaude Fable 584.6Margin← 3.6GLM-5.281.0
KnowledgeClaude Fable 5Not measuredMarginNo overlapGLM-5.259.6
MathClaude Fable 5Not measuredMarginNo overlapGLM-5.295.9
MultimodalClaude Fable 557.9MarginNo overlapGLM-5.2Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Fable 5B · GLM-5.2

  1. SWE-bench Pro

    Coding
    Source ↗
    A 80%B 62.1%
    Winner: Claude Fable 5Δ 17.9
    SWE-bench Pro: Claude Fable 5 scored 80%; GLM-5.2 scored 62.1%. Claude Fable 5 wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 84.3%B 81%
    Winner: Claude Fable 5Δ 3.3
    Terminal-Bench 2.0: Claude Fable 5 scored 84.3%; GLM-5.2 scored 81%. Claude Fable 5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Fable 5GLM-5.2Comparison
Input / output priceUSD per 1M tokensClaude Fable 5$10 input / $50 outputGLM-5.2$1.4 input / $4.4 outputGLM-5.2 has the lower combined listed price.
Generation speedtokens per secondClaude Fable 5Not availableGLM-5.2Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Fable 5Not availableGLM-5.2Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Fable 51M+GLM-5.21MClaude Fable 5 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Fable 5 wins
BenchmarkClaude Fable 5GLM-5.2Result
Terminal-Bench 2.0Source 84.3%81%Claude Fable 5 leads
OSWorld-VerifiedSource 85%—Not comparable
GDPval-AASource 17481514Claude Fable 5 leads
AA Agentic IndexSource 52.8%43.1%Claude Fable 5 leads
τ²-bench resultsSource 98.5%99.1%GLM-5.2 leads
GDPval-AASource 62.4%50.7%Claude Fable 5 leads
AA BriefcaseSource 15741260Claude Fable 5 leads
AA AutomationBenchSource 48.6%27.8%Claude Fable 5 leads
AA EnterpriseOps-GymSource 51.1%42.7%Claude Fable 5 leads
AA Harvey LABSource 93.6%91.0%Claude Fable 5 leads
AA Tau3 BankingSource 26.8%26.8%Tie
terminalBenchHardSource 62.9%50.8%Claude Fable 5 leads
aaTerminalBench21Source 84.6%77.9%Claude Fable 5 leads
MCP AtlasSource —76.8%Not comparable
ToolathlonSource —48.2%Not comparable
APEX-Agents-AASource —33.7%Not comparable
ResearchClawBenchSource —20.7%Not comparable
AA ITBenchSource —42.7%Not comparable
CodingClaude Fable 5 wins
BenchmarkClaude Fable 5GLM-5.2Result
SWE-bench VerifiedSource 95%—Not comparable
SWE-bench ProSource 80%62.1%Claude Fable 5 leads
FrontierCode 1.1 MainSource 53.5%—Not comparable
Terminal-Bench 2.0Source 84.3%81.0%Claude Fable 5 leads
cursorBench31Source 70.6%—Not comparable
cursorBench32Source 70.5%55.0%Claude Fable 5 leads
VulcanBench v3Source 87.0%—Not comparable
AA Coding IndexSource 76.5%68.8%Claude Fable 5 leads
AA-SciCodeSource 60.2%50.5%Claude Fable 5 leads
NL2RepoSource —48.9%Not comparable
ProgramBenchSource —63.7%Not comparable
Reasoning
BenchmarkClaude Fable 5GLM-5.2Result
AA-LCRSource 70.0%71.3%GLM-5.2 leads
CritPtSource 28.6%20.9%Claude Fable 5 leads
Knowledge
BenchmarkClaude Fable 5GLM-5.2Result
Artificial Analysis Intelligence IndexSource 59.9%51.1%Claude Fable 5 leads
AA-GPQA DiamondSource 92.6%89.5%Claude Fable 5 leads
AA-HLESource 53.3%40.1%Claude Fable 5 leads
AA-Omniscience IndexSource 40.2%4.0%Claude Fable 5 leads
AA-Omniscience AccuracySource 61.4%25.1%Claude Fable 5 leads
AA-Omniscience Hallucination RateSource 54.9%28.1%GLM-5.2 leads
GPQASource —91.2%Not comparable
GPQA-DSource —91.2%Not comparable
HLESource —54.7%Not comparable
HLE w/o toolsSource —40.5%Not comparable
AA Openness IndexSource —44.4%Not comparable
Math
BenchmarkClaude Fable 5GLM-5.2Result
AIME26Source —99.2%Not comparable
HMMT Nov 2025Source —94.4%Not comparable
HMMT Feb 2026Source —92.5%Not comparable
MMAnswerBenchSource —91.0%Not comparable
Multimodal
BenchmarkClaude Fable 5GLM-5.2Result
Blueprint-Bench 2Source 38.6%—Not comparable
OfficeQA ProSource 57.9%—Not comparable
Design Arena WebsiteSource 13321340GLM-5.2 leads
Inst. Following
BenchmarkClaude Fable 5GLM-5.2Result
AA-IFBenchSource 63.5%73.3%GLM-5.2 leads
Frequently Asked Questions (3)

Which is better, Claude Fable 5 or GLM-5.2?

Claude Fable 5 is ahead on BenchLM's BenchAlign leaderboard, 83.68 to 63.96. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 80% and 62.1%.

Which is better for coding, Claude Fable 5 or GLM-5.2?

Claude Fable 5 has the edge for coding in this comparison, averaging 89.2 versus 62.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Fable 5 or GLM-5.2?

Claude Fable 5 has the edge for agentic tasks in this comparison, averaging 84.6 versus 81. Inside this category, AA Briefcase is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.