Head-to-head comparison

GPT-6 Astra 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: 127
distinct benchmarks: 11
latest retrieval: 2026-10-15

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 GPT-6 Astra and GLM-5.1
Attribute	GPT-6 Astra	GLM-5.1
Provider	OpenAI	Z.ai
Released	Sep 3, 2026	Apr 7, 2026
Availability	Limited access	Open Source
Model type	Proprietary	Open Weights
Parameters	Not published	744B, 40B active
Architecture	Not published	Mixture of Experts
Context window	1,050,000 tokens	200,000 tokens
Knowledge cutoff	April 30, 2026	Not published
Technical sources	Model, Context	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 GPT-6 Astra and GLM-5.1
Price type	GPT-6 Astra	GLM-5.1
API input	$10 ≤272K / $20 >272K	$1.4
API output	$50 ≤272K / $75 >272K	$4.4
Cache read	$1 ≤272K / $2 >272K	$0.26
Cache write (5 min.)	$12.5 ≤272K / $25 >272K	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

GPT-6 AstraGLM-5.1

API inputUSD per 1M tokens, base tier

GPT-6 Astra$10

GLM-5.1$1.4

API outputUSD per 1M tokens, base tier

GPT-6 Astra$50

GLM-5.1$4.4

Cache readUSD per 1M tokens, base tier

GPT-6 Astra$1

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 GPT-6 Astra and GLM-5.1
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GPT-6 Astra	OpenAI	Direct from developerUp to 272,000 context tokens	$10	$50	Source09/22/2026
	OpenAI	Direct from developerAbove 272,000 context tokens	$20	$75	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-west-2	$11	$55	Source10/17/2026
	Azure	Via OpenRouterazure	$10	$50	Source10/17/2026
	Azure	Via OpenRouterazure/us	$11	$55	Source10/17/2026
	OpenAI	Via OpenRouteropenai	$10	$50	Source10/17/2026
	OpenAI	Via OpenRouteropenai/fast	$20	$100	Source10/17/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $5	Lowest listed price: $25	Source10/17/2026
	OpenAI	Via OpenRouteropenai/ultrafast	$60	$300	Source10/17/2026
GLM-5.1	Z.ai	Direct from developerStandard API	$1.4	$4.4	Source09/22/2026
	Alibaba	Via OpenRouteralibaba/fp8	$1.33	$4.18	Source10/17/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$1.26	$3.96	Source10/17/2026
	Baidu	Via OpenRouterbaidu/fp8	Lowest listed price: $0.9646	Lowest listed price: $3.0316	Source10/17/2026
	Chutes	Via OpenRouterchutes/fp8	$0.98	$3.08	Source10/17/2026
	Friendli	Via OpenRouterfriendli	$1.4	$4.4	Source10/17/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.4	$4.4	Source10/17/2026
	Nebius	Via OpenRouternebius/fp8	$1.4	$4.4	Source10/17/2026
	Novita	Via OpenRouternovita/fp8	$1.38	$4.4	Source10/17/2026
	Phala	Via OpenRouterphala	$1.21	$4.2	Source10/17/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.19	$3.74	Source10/17/2026
	StreamLake	Via OpenRouterstreamlake/fp8	$0.966	$3.036	Source10/17/2026
	Venice	Via OpenRoutervenice/fp8	$1.4014	$4.4044	Source10/17/2026
	Z.AI	Via OpenRouterz-ai/fp8	$1.4	$4.4	Source10/17/2026

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.

Not enough directly matched categories for a reliable radar

Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

GPT-6 AstraGLM-5.1

Code MigrationOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra67.74 %

GLM-5.125.768 %

Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical

GPT-6 Astra53.54 %

GLM-5.144.792 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical

GPT-6 Astra5.417 %

GLM-5.10 %

Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical

GPT-6 Astra39.423 %

GLM-5.127.885 %

LMArena Code Arena WebDevOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra1,780.244

GLM-5.11,508.395

LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra1,476.716

GLM-5.11,465.374

MedCodeOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra48.486 %

GLM-5.141.604 %

MedScribeOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra87.908 %

GLM-5.172.27 %

ProgramBenchOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra5.5 %

GLM-5.10 %

Terminal-Bench 2.1Overall. Higher is better. Test setup not documented as identical

GPT-6 Astra87.266 %

GLM-5.156.929 %

Vibe Code Bench v1.1Overall. Higher is better. Test setup not documented as identical

GPT-6 Astra89.594 %

GLM-5.131.456 %

Code MigrationCLI. Higher is better. Test setup not documented as identical

GPT-6 Astra67.463 %

GLM-5.118.833 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-6 Astra and GLM-5.1
Benchmark and task	GPT-6 Astra	GLM-5.1	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value67.74 %	25.768 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value53.54 %	44.792 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value5.417 %	0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value39.423 %	27.885 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev GLM-5.1: Snapshot: glm-5.1, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.GLM-5.1: Arena rating from 10,746 published pairwise votes.	Higher measured value1,780.244 95% confidence interval: ±10.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,508.395 95% confidence interval: ±6.771The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 11,674 published pairwise votes.GLM-5.1: Arena rating from 62,175 published pairwise votes.	Higher measured value1,476.716 95% confidence interval: ±6.385The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,465.374 95% confidence interval: ±3.602The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens	Higher measured value48.486 %	41.604 %	Vals AI Source details Data as of: 10/13/2026
MedScribeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens	Higher measured value87.908 %	72.27 %	Vals AI Source details Data as of: 10/13/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value5.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value87.266 %	56.929 %	Vals AI Source details Data as of: 09/28/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens GLM-5.1: Harness: OpenHands, Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value89.594 %	31.456 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value67.463 %	18.833 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value48.318 %	43.276 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value88.768 %	71.377 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value53.03 %	31.818 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev GLM-5.1: Snapshot: glm-5.1, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.GLM-5.1: Arena rating from 10,746 published pairwise votes.	Higher measured value1,780.244 95% confidence interval: ±10.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,508.395 95% confidence interval: ±6.771The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlBusiness, management and finance Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,061 published pairwise votes.GLM-5.1: Arena rating from 12,030 published pairwise votes.	Higher measured value1,472.34 95% confidence interval: ±13.336The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,465.499 95% confidence interval: ±6.25The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value50 %	1 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-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: 09/28/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value68.571 %	46.571 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value40.252 %	32.68 %	Vals AI Source details Data as of: 10/12/2026
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 betterGPT-6 Astra: Reasoning: max, 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: 10/12/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value87.482 %	80.005 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev-html Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev GLM-5.1: Snapshot: glm-5.1, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 1,129 published pairwise votes.GLM-5.1: Arena rating from 1,210 published pairwise votes.	Higher measured value1,780.13 95% confidence interval: ±22.887The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,509.083 95% confidence interval: ±18.189The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 877 published pairwise votes.GLM-5.1: Arena rating from 4,311 published pairwise votes.	Higher measured value1,514.537 95% confidence interval: ±19.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,512.757 95% confidence interval: ±9.666The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value5.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value87.778 %	37.778 %	Vals AI Source details Data as of: 09/28/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value4.469 / 5	3.544 / 5	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	37.758 %	Higher measured value41.557 %	Vals AI Source details Data as of: 10/12/2026
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 betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value86.022 %	53.405 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value32.558 %	23.256 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev-react Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev GLM-5.1: Snapshot: glm-5.1, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 3,422 published pairwise votes.GLM-5.1: Arena rating from 8,193 published pairwise votes.	Higher measured value1,804.405 95% confidence interval: ±13.548The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,505.232 95% confidence interval: ±7.631The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlCoding Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,659 published pairwise votes.GLM-5.1: Arena rating from 16,961 published pairwise votes.	Higher measured value1,543.161 95% confidence interval: ±11.756The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,512.302 95% confidence interval: ±5.549The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: raw test pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value85.417 %	50.879 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value86.061 %	65.455 %	Vals AI Source details Data as of: 09/28/2026
Finance Agent (v2)Disclosure Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value61.684 %	52.713 %	Vals AI Source details Data as of: 10/12/2026
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 betterGPT-6 Astra: Reasoning: max, 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: 10/12/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value83.821 %	81.655 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlCreative writing Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,620 published pairwise votes.GLM-5.1: Arena rating from 12,127 published pairwise votes.	Higher measured value1,449.578 95% confidence interval: ±12.436The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,447.334 95% confidence interval: ±6.452The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)Earnings Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value69.474 %	56.958 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkBanking Finance · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value88.104 %	71.004 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchCivil Litigation · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value40.741 %	22.222 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlEnglish Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 4,703 published pairwise votes.GLM-5.1: Arena rating from 26,692 published pairwise votes.	Higher measured value1,485.113 95% confidence interval: ±9.08The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,480.944 95% confidence interval: ±4.656The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)Financial Modeling Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value21.585 %	13.466 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkBanking Finance · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, 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: 10/12/2026
Legal Research BenchCivil Litigation · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value88.669 %	83.513 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlEntertainment, sports and media Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,996 published pairwise votes.GLM-5.1: Arena rating from 14,753 published pairwise votes.	Higher measured value1,458.633 95% confidence interval: ±11.598The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,442.133 95% confidence interval: ±5.949The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)General Qualitative Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value68.425 %	63.665 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkBankruptcy Restructuring · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value82.007 %	75.433 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchConstitutional / Civil Rights · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	26.316 %	Higher measured value34.211 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlExcluding ties Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 8,636 published pairwise votes.GLM-5.1: Arena rating from 46,453 published pairwise votes.	Higher measured value1,488.868 95% confidence interval: ±8.374The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,471.538 95% confidence interval: ±4.716The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)General Quantitative Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value78.779 %	61.87 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkBankruptcy Restructuring · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, 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: 10/12/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	82.609 %	Higher measured value84.883 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlExpert prompts Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 1,132 published pairwise votes.GLM-5.1: Arena rating from 6,634 published pairwise votes.	Higher measured value1,509.902 95% confidence interval: ±17.672The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,495.565 95% confidence interval: ±7.941The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)Market Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value65.549 %	51.861 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkCapital Markets · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value91.373 %	71.765 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchCriminal · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	No direct winner29.825 %	No direct winner29.825 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlFrench Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 333 published pairwise votes.GLM-5.1: Arena rating from 2,199 published pairwise votes.	Higher measured value1,489.442 95% confidence interval: ±32.984The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,482.622 95% confidence interval: ±14.364The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Finance Agent (v2)Precedents Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value30.289 %	17.764 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkCapital Markets · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, 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: 10/12/2026
Legal Research BenchCriminal · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value83.205 %	78.143 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlGerman Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control GLM-5.1: Snapshot: glm-5.1, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 176 published pairwise votes.GLM-5.1: Arena rating from 992 published pairwise votes.	Higher measured value1,480.596 95% confidence interval: ±44.81The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,465.541 95% confidence interval: ±19.673The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
Harvey's Legal Agent BenchmarkCorporate Governance · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GLM-5.1: Temperature: 1, Top P: 0.95, Output limit: 131,072 tokens	Higher measured value88.356 %	72.945 %	Vals AI Source details Data as of: 10/12/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 4ae5d8eeb9a9

GPT-6 Astra

Unavailable in this round

GLM-5.1

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

GPT-6 Astra

Reasoning (requested): high

Current attempt

Run date: Sep 7, 2026
API provider: openrouter
Requested API model: openai/gpt-6-astra
API model reported in response: openai/gpt-6-astra
Reasoning setting: high
Pinned endpoint: OpenAI | openai/gpt-6-astra-20260903
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: 141.7 s

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

GLM-5.1

Output withheld for safety

Reasoning (requested): high

Current attempt

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: z-ai/glm-5.1
API model reported in response: z-ai/glm-5.1
Reasoning setting: high
Pinned endpoint: Z.AI | z-ai/glm-5.1-20260406
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 141.6 s

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

Earlier attempts (3)

Oct 2, 2026Output withheld for safetyReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

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 GPT-6 Astra and GLM-5.1 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

GPT-6 Astra vs. GLM-5.1

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

GPT-6 Astra

GLM-5.1

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons