Head-to-head comparison

Grok 4.3 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: 173
distinct benchmarks: 20
latest retrieval: 2026-09-04

First modelSecond model

Specifications

General specifications

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

Specifications for Grok 4.3 and GLM-5.1
Attribute	Grok 4.3	GLM-5.1
Provider	xAI	Z.ai
Released	May 6, 2026	Apr 7, 2026
Availability	Active	Open Source
Model type	Proprietary	Open Weights
Parameters	Not published	744B, 40B active
Architecture	Not published	Mixture of Experts
Context window	1,000,000 tokens	200,000 tokens
Knowledge cutoff	Not published	Not published
Technical sources	Model	Model, 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 Grok 4.3 and GLM-5.1
Price type	Grok 4.3	GLM-5.1
API input	$1.25 ≤200K / $2.5 >200K	$1.4
API output	$2.5 ≤200K / $5 >200K	$4.4
Cache read	$0.2 ≤200K / $0.4 >200K	$0.26
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	08/11/2026 Source	07/30/2026 Source

Grok 4.3GLM-5.1

API inputUSD per 1M tokens, base tier

Grok 4.3$1.25

GLM-5.1$1.4

API outputUSD per 1M tokens, base tier

Grok 4.3$2.5

GLM-5.1$4.4

Cache readUSD per 1M tokens, base tier

Grok 4.3$0.2

GLM-5.1$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 Grok 4.3 and GLM-5.1
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Grok 4.3	xAI	Direct from developerUp to 200,000 context tokens	Lowest listed price: $1.25	Lowest listed price: $2.5	Source08/11/2026
	xAI	Direct from developerAbove 200,000 context tokens	$2.5	$5	Source08/11/2026
	xAI	Via OpenRouterxai	Lowest listed price: $1.25	Lowest listed price: $2.5	Source09/08/2026
	xAI	Via OpenRouterxai/priority	$2.5	$5	Source09/08/2026
	xAI	Via OpenRouterxai/zdr	Lowest listed price: $1.25	Lowest listed price: $2.5	Source09/08/2026
	xAI	Via OpenRouterxai/zdr/priority	$2.5	$5	Source09/08/2026
GLM-5.1	Z.ai	Direct from developerStandard API	$1.4	$4.4	Source07/30/2026
	Alibaba	Via OpenRouteralibaba/fp8	$1.33	$4.18	Source09/08/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$1.26	$3.96	Source09/08/2026
	Baidu	Via OpenRouterbaidu/fp8	$1.4	$4.4	Source09/08/2026
	Chutes	Via OpenRouterchutes/fp8	$0.98	$3.08	Source09/08/2026
	Crusoe	Via OpenRoutercrusoe/fp8	$1.2	$4.4	Source09/08/2026
	DeepInfra	Via OpenRouterdeepinfra/fp4	$1.05	$3.5	Source09/08/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.3	$4.3	Source09/08/2026
	Friendli	Via OpenRouterfriendli	$1.4	$4.4	Source09/08/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.4	$4.4	Source09/08/2026
	Nebius	Via OpenRouternebius/fp8	$1.4	$4.4	Source09/08/2026
	Novita	Via OpenRouternovita/fp8	$1.38	$4.4	Source09/08/2026
	Phala	Via OpenRouterphala	$1.21	$4.2	Source09/08/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.19	$3.74	Source09/08/2026
	StreamLake	Via OpenRouterstreamlake/fp8	Lowest listed price: $0.966	Lowest listed price: $3.036	Source09/08/2026
	Venice	Via OpenRoutervenice/fp8	$1.54	$4.84	Source09/08/2026
	Z.AI	Via OpenRouterz-ai/fp8	$1.4	$4.4	Source09/08/2026

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.

Grok 4.3

GLM-5.1

Coding: 80 / 99.4 (6 benchmark families)

Reasoning: 98.8 / 96.2 (2 benchmark families)

Mathematics: 96.7 / 100 (1 benchmark family)

Knowledge: 98.2 / 100 (2 benchmark families)

Finance: 95.5 / 98.5 (4 benchmark families)

Legal: 88.1 / 75 (4 benchmark families)

Agentic tasks: 77.1 / 100 (1 benchmark family)

Productivity: 83.6 / 100 (1 benchmark family)

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

Grok 4.3GLM-5.1

Code MigrationOverall. Higher is better. No documented setup difference

Grok 4.36.795 %

GLM-5.125.768 %

CorpFin v2Overall. Higher is better. No documented setup difference

Grok 4.368.532 %

GLM-5.164.452 %

Finance Agent (v2)Overall. Higher is better. No documented setup difference

Grok 4.337.728 %

GLM-5.144.792 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Grok 4.391.414 %

GLM-5.184.518 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference

Grok 4.30.417 %

GLM-5.10 %

Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference

Grok 4.315.385 %

GLM-5.127.885 %

LegalBenchOverall. Higher is better. No documented setup difference

Grok 4.384.458 %

GLM-5.184.394 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Grok 4.384.494 %

GLM-5.181.38 %

LMArena Text, Style ControlOverall. Higher is better. No documented setup difference

Grok 4.31,442.599

GLM-5.11,466.019

MedCodeOverall. Higher is better. No documented setup difference

Grok 4.338.068 %

GLM-5.141.604 %

MedScribeOverall. Higher is better. No documented setup difference

Grok 4.374.399 %

GLM-5.172.27 %

MMLU-ProOverall. Higher is better. No documented setup difference

Grok 4.385.838 %

GLM-5.186.9 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Grok 4.3 and GLM-5.1
Benchmark and task	Grok 4.3	GLM-5.1	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	6.795 %	Winner25.768 %	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	Winner68.532 %	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	37.728 %	Winner44.792 %	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	Winner91.414 %	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	Winner0.417 %	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	15.385 %	Winner27.885 %	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	Winner84.458 %	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	Winner84.494 %	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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 45,403 anonymous pairwise votes.	1,442.599 95% confidence interval: ±3.771The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,466.019 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	38.068 %	Winner41.604 %	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	Winner74.399 %	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	85.838 %	Winner86.9 %	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	Tie0 %	Tie0 %	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	51.691 %	Winner61.84 %	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	71.4 %	Winner76.4 %	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	70.81 %	Winner71.194 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details No documented difference in the test setupVersion: 2.0Metric: accuracyScoring: Higher is better	43.446 %	Winner53.933 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	41.948 %	Winner56.929 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95	Higher measured value70.047 %	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	19.403 %	Winner31.456 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	9.06 %	Higher measured value18.833 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value66.783 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95	31.863 %	Higher measured value43.276 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	61.594 %	Higher measured value71.377 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	25.758 %	Higher measured value31.818 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value89.912 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	98.447 %	Higher measured value98.754 %	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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 9,036 anonymous pairwise votes.	1,439.103 95% confidence interval: ±6.526The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,464.877 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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	93.305 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	0 %	Higher measured value1 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	83.505 %	Higher measured value88.66 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	60.589 %	Higher measured value61.538 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.0Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGrok 4.3: Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	66.667 %	Higher measured value75 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	75 %	Higher measured value83.333 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95	37.766 %	Higher measured value44.79 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	0 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value68.765 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95	26.373 %	Higher measured value32.68 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value89.899 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	73.866 %	Higher measured value80.005 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value81.805 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value66 %	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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,641 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 2,742 anonymous pairwise votes.	1,479.363 95% confidence interval: ±10.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,516.722 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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value92.902 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 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: 08/09/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	No direct winner33.333 %	No direct winner33.333 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value81.03 %	80.851 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.0Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGrok 4.3: Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	24.444 %	Higher measured value36.667 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	14.444 %	Higher measured value37.778 %	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	70.588 %	Winner72.549 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	3.098 / 5	Higher measured value3.544 / 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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value70.047 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95	35.857 %	Higher measured value41.557 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value68.1 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	13.953 %	Higher measured value23.256 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value89.182 %	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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	Higher measured value89.034 %	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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 18,240 anonymous pairwise votes.GLM-5.1: Style-controlled Arena rating from 12,659 anonymous pairwise votes.	1,487.832 95% confidence interval: ±5.841The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,513.669 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 betterGrok 4.3: Temperature: 0.7, Top P: 0.95	91.608 %	Higher measured value91.844 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	22.105 %	Higher measured value50.879 %	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 betterGrok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	38.095 %	Higher measured value45.238 %	Vals AI Source details Data as of: 08/08/2026
Terminal-Bench 2.0Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGrok 4.3: Temperature: 0.7, Top P: 0.95 GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	52.121 %	Higher measured value61.818 %	Vals AI Source details Data as of: 06/04/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Grok 4.3

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: x-ai/grok-4.3
API model reported in response: x-ai/grok-4.3
Pinned endpoint: xAI | x-ai/grok-4.3-20260430
Reasoning setting: high
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 149 s

Visually reviewed. This individual test does not establish overall model quality.

GLM-5.1

API access was unavailable for this run. The model was not evaluated.

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: z-ai/glm-5.1
Pinned endpoint: Z.AI | z-ai/glm-5.1-20260406
Reasoning setting: high
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

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

Compare Grok 4.3 and GLM-5.1 with other leading models using the same data and benchmark logic.

View the complete LLM comparison