Skip to main content

Head-to-head comparison

Claude Fable 5 vs. GLM-5.1

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series
169
distinct benchmarks
19
latest retrieval
2026-09-04

Change model selection

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Claude Fable 5 and GLM-5.1
AttributeClaude Fable 5GLM-5.1
ProviderAnthropicZ.ai
ReleasedJun 9, 2026Apr 7, 2026
AvailabilityActiveOpen Source
Model typeProprietaryOpen Weights
ParametersNot published744B, 40B active
ArchitectureNot publishedMixture of Experts
Context window1,000,000 tokens200,000 tokens
Knowledge cutoffJanuary 2026Not published
Technical sourcesModel, Context, Knowledge cutoffModel, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Claude Fable 5 and GLM-5.1
Price typeClaude Fable 5GLM-5.1
API input$10$1.4
API output$50$4.4
Cache read$1$0.26
Cache write (5 min.)$12.5Not listed
Cache write (1 hr.)$20Not listed
Price verified07/30/2026 Source07/30/2026 Source
Claude Fable 5GLM-5.1
API inputUSD per 1M tokens, base tier
Claude Fable 5$10
GLM-5.1Lower price$1.4
API outputUSD per 1M tokens, base tier
Claude Fable 5$50
GLM-5.1Lower price$4.4
Cache readUSD per 1M tokens, base tier
Claude Fable 5$1
GLM-5.1Lower price$0.26

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Claude Fable 5 and GLM-5.1
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Fable 5AnthropicDirect from developerStandard APILowest listed price: $10Lowest listed price: $50Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $10Lowest listed price: $50Source09/07/2026
AnthropicVia OpenRouteranthropicLowest listed price: $10Lowest listed price: $50Source09/07/2026
AzureVia OpenRouterazureLowest listed price: $10Lowest listed price: $50Source09/07/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $10Lowest listed price: $50Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/europe$11$55Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $10Lowest listed price: $50Source09/07/2026
GLM-5.1Z.aiDirect from developerStandard API$1.4$4.4Source07/30/2026
AlibabaVia OpenRouteralibaba/fp8$1.33$4.18Source09/07/2026
AtlasCloudVia OpenRouteratlas-cloud/fp8$1.26$3.96Source09/07/2026
BaiduVia OpenRouterbaidu/fp8$1.4$4.4Source09/07/2026
ChutesVia OpenRouterchutes/fp8$0.98$3.08Source09/07/2026
CrusoeVia OpenRoutercrusoe/fp8$1.2$4.4Source09/07/2026
DeepInfraVia OpenRouterdeepinfra/fp4$1.05$3.5Source09/07/2026
DigitalOceanVia OpenRouterdigitalocean$1.3$4.3Source09/07/2026
FriendliVia OpenRouterfriendli$1.4$4.4Source09/07/2026
GMICloudVia OpenRoutergmicloud/fp8Lowest listed price: $0.91Lowest listed price: $2.86Source09/07/2026
NebiusVia OpenRouternebius/fp8$1.4$4.4Source09/07/2026
NovitaVia OpenRouternovita/fp8$1.38$4.4Source09/07/2026
PhalaVia OpenRouterphala$1.21$4.2Source09/07/2026
SiliconFlowVia OpenRoutersiliconflow/fp8$1.19$3.74Source09/07/2026
StreamLakeVia OpenRouterstreamlake/fp8$0.966$3.036Source09/07/2026
VeniceVia OpenRoutervenice/fp8$1.54$4.84Source09/07/2026
Z.AIVia OpenRouterz-ai/fp8$1.4$4.4Source09/07/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksProductivity
Claude Fable 5
GLM-5.1
Coding: 100 / 58.4 (6 benchmark families)
Reasoning: 100 / 93.9 (2 benchmark families)
Mathematics: 100 / 97 (1 benchmark family)
Knowledge: 100 / 96.2 (2 benchmark families)
Finance: 100 / 89.8 (4 benchmark families)
Legal: 100 / 62.4 (4 benchmark families)
Agentic tasks: 100 / 70.7 (1 benchmark family)
Productivity: 100 / 87.8 (1 benchmark family)

48 matched rows from 19 benchmark families were considered. The radar shows 8 of 11 comparable categories.

Claude Fable 5GLM-5.1
Code MigrationOverall. Higher is better. No documented setup difference
Claude Fable 5Winner55.065 %
GLM-5.125.768 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Fable 5Winner71.834 %
GLM-5.164.452 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Fable 5Winner56.314 %
GLM-5.144.792 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Claude Fable 5Winner93.182 %
GLM-5.184.518 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Fable 5Winner11.25 %
GLM-5.10 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Fable 5Winner49.519 %
GLM-5.127.885 %
LegalBenchOverall. Higher is better. No documented setup difference
Claude Fable 5Winner88.561 %
GLM-5.184.394 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Claude Fable 5Winner89.778 %
GLM-5.181.38 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Claude Fable 5Winner1,507.405
GLM-5.11,466.019
MedCodeOverall. Higher is better. No documented setup difference
Claude Fable 5Winner56.07 %
GLM-5.141.604 %
MedScribeOverall. Higher is better. No documented setup difference
Claude Fable 5Winner88.522 %
GLM-5.172.27 %
MMLU-ProOverall. Higher is better. No documented setup difference
Claude Fable 5Winner91.502 %
GLM-5.186.9 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Fable 5 and GLM-5.1
Benchmark and taskClaude Fable 5GLM-5.1Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner55.065 %
25.768 %
Vals AI
Source details
Data as of: 09/03/2026
CorpFin v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner71.834 %
64.452 %
Vals AI
Source details
Data as of: 08/12/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner56.314 %
44.792 %
Vals AI
Source details
Data as of: 09/03/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner93.182 %
84.518 %
Vals AI
Source details
Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better
Winner11.25 %
0 %
Vals AI
Source details
Data as of: 09/03/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
Winner49.519 %
27.885 %
Vals AI
Source details
Data as of: 09/03/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner88.561 %
84.394 %
Vals AI
Source details
Data as of: 09/01/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.778 %
81.38 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 26,977 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 45,403 anonymous pairwise votes.
Winner1,507.405
95% confidence interval: ±4.978The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,466.019
95% confidence interval: ±3.982The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner56.07 %
41.604 %
Vals AI
Source details
Data as of: 09/03/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner88.522 %
72.27 %
Vals AI
Source details
Data as of: 09/03/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner91.502 %
86.9 %
Vals AI
Source details
Data as of: 09/01/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner2 %
0 %
Vals AI
Source details
Data as of: 09/01/2026
Public Benefits Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
Winner70.433 %
61.84 %
Vals AI
Source details
Data as of: 09/01/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner95 %
76.4 %
Vals AI
Source details
Data as of: 09/01/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner76.942 %
71.194 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better
Winner80.524 %
56.929 %
Vals AI
Source details
Data as of: 09/03/2026
Vals IndexCorpFin v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value71.562 %
65.268 %
Vals AI
Source details
Data as of: 08/09/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner90.352 %
31.456 %
Vals AI
Source details
Data as of: 09/03/2026
Code MigrationCLI
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value60.087 %
18.833 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Exact Pages
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value66.9 %
61.772 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Adjustments
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value51.092 %
43.276 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondFew-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value92.929 %
85.787 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value92.035 %
71.377 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value57.576 %
31.818 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchConclusion Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value91.775 %
89.575 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value98.758 %
98.754 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 5,567 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 9,036 anonymous pairwise votes.
Winner1,501.942
95% confidence interval: ±8.642The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,464.877
95% confidence interval: ±7.07The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBiology
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
93.584 %
Higher measured value93.724 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchAlmost Resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value33 %
1 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified<15 min fix
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value95.876 %
88.66 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Correctness
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value65.822 %
61.538 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value100 %
83.333 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexFinance Agent v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value56.349 %
44.79 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCOBOL
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
40 %
Higher measured value46.571 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Max Fitting Context
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value77.04 %
66.317 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)All-Pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value45.694 %
32.68 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondZero-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value93.434 %
83.249 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value90.224 %
80.005 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchInterpretation Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value86.863 %
81.709 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value79.714 %
57.429 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlChinese
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 1,671 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 2,742 anonymous pairwise votes.
Winner1,554.267
95% confidence interval: ±15.295The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,516.722
95% confidence interval: ±12.084The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBusiness
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value93.156 %
91.128 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchFully Resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value2 %
0 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified>4 hours
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value100 %
33.333 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value88.062 %
80.851 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value70 %
37.778 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexSWE-bench
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is better
Winner97.059 %
72.549 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCode Quality
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value4.442 / 5
3.544 / 5
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Shared Max Context
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value71.562 %
65.268 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Comparables
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value43.986 %
41.557 %
Vals AI
Source details
Data as of: 08/06/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value91.398 %
53.405 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchBusiness & Commercial · All-pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value51.163 %
23.256 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchIssue Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value92.064 %
89.02 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Medium
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value90.862 %
87.958 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlCoding
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 7,243 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 12,659 anonymous pairwise votes.
Winner1,551.491
95% confidence interval: ±7.795The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,513.669
95% confidence interval: ±6.252The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProChemistry
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value93.905 %
91.844 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchRaw Pass Rate
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value76.803 %
50.879 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified1-4 hours
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value92.857 %
45.238 %
Vals AI
Source details
Data as of: 08/08/2026
Terminal-Bench 2.1Medium
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
Higher measured value84.848 %
65.455 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexTerminal-Bench 2.1
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is better
Winner80.524 %
56.929 %
Vals AI
Source details
Data as of: 08/09/2026
Finance Agent (v2)Disclosure Analysis
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value68.82 %
52.713 %
Vals AI
Source details
Data as of: 08/06/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Task fully resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/07/2026

Key to the marks:better valuebetter, but not conclusivetie

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Related LLM comparisons

Compare Claude Fable 5 and GLM-5.1 with other leading models using the same data and benchmark logic.

View the complete LLM comparison