Head-to-head comparison

GPT-6 Astra vs. GPT-5.4 mini

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

shared result series: 193
distinct benchmark metrics: 27
latest retrieval: 2026-10-19

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 GPT-5.4 mini
Attribute	GPT-6 Astra	GPT-5.4 mini
Provider	OpenAI	OpenAI
Released	Sep 3, 2026	Mar 17, 2026
Availability	Limited access	Active
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,050,000 tokens	400,000 tokens
Knowledge cutoff	April 30, 2026	August 31, 2025
Technical sources	Model, Context	Model

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 GPT-5.4 mini
Price type	GPT-6 Astra	GPT-5.4 mini
API input	$10 ≤272K / $20 >272K	$0.75
API output	$50 ≤272K / $75 >272K	$4.5
Cache read	$1 ≤272K / $2 >272K	$0.075
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 AstraGPT-5.4 mini

API inputUSD per 1M tokens, base tier

GPT-6 Astra$10

GPT-5.4 mini$0.75

API outputUSD per 1M tokens, base tier

GPT-6 Astra$50

GPT-5.4 mini$4.5

Cache readUSD per 1M tokens, base tier

GPT-6 Astra$1

GPT-5.4 mini$0.075

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 GPT-5.4 mini
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	Source10/19/2026
	Azure	Via OpenRouterazure	$10	$50	Source10/19/2026
	Azure	Via OpenRouterazure/us	$11	$55	Source10/19/2026
	OpenAI	Via OpenRouteropenai	$10	$50	Source10/19/2026
	OpenAI	Via OpenRouteropenai/fast	$20	$100	Source10/19/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $5	Lowest listed price: $25	Source10/19/2026
	OpenAI	Via OpenRouteropenai/ultrafast	$60	$300	Source10/19/2026
GPT-5.4 mini	OpenAI	Direct from developerStandard API	$0.75	$4.5	Source09/22/2026
	Azure	Via OpenRouterazure	$0.75	$4.5	Source10/19/2026
	Azure	Via OpenRouterazure/us	$0.825	$4.95	Source10/19/2026
	OpenAI	Via OpenRouteropenai	$0.75	$4.5	Source10/19/2026
	OpenAI	Via OpenRouteropenai/fast	$1.5	$9	Source10/19/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $0.375	Lowest listed price: $2.25	Source10/19/2026

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.

GPT-6 Astra

GPT-5.4 mini

Coding: 100 / 3.4 (1 benchmark family)

Reasoning: 100 / 63.1 (3 benchmark families)

Knowledge: 100 / 45.2 (1 benchmark family)

Agentic tasks: 100 / 50.2 (3 benchmark families)

Multimodal: 100 / 84.3 (1 benchmark family)

Overall: 100 / 45.9 (1 benchmark family)

15 matched rows from 10 benchmark families were considered. The radar shows 6 of 6 comparable categories.

GPT-6 AstraGPT-5.4 mini

AA-BriefcaseOverall. Higher is better. No documented setup difference

GPT-6 Astra1,546.7 elo

GPT-5.4 mini719.36 elo

AA-LCROverall. Higher is better. No documented setup difference

GPT-6 Astra80.0%

GPT-5.4 mini77.0%

AA-OmniscienceOverall. Higher is better. No documented setup difference

GPT-6 Astra43.417 points

GPT-5.4 mini-18.917 points

AA-Omniscience AccuracyOverall. Higher is better. No documented setup difference

GPT-6 Astra61.9%

GPT-5.4 mini37.5%

AA-Omniscience Hallucination RateOverall. Lower is better. No documented setup difference

GPT-6 Astra48.3%

GPT-5.4 mini90.2%

Artificial Analysis Intelligence IndexOverall. Higher is better. No documented setup difference

GPT-6 Astra52.386 points

GPT-5.4 mini24.068 points

AutomationBench-AAOverall. Higher is better. No documented setup difference

GPT-6 Astra67.2%

GPT-5.4 mini26.2%

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

GPT-6 Astra67.74 %

GPT-5.4 mini12.936 %

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

GPT-6 Astra71.7 %

GPT-5.4 mini45.426 %

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

GPT-6 Astra53.54 %

GPT-5.4 mini45.36 %

GDP.pdfOverall. Higher is better. No documented setup difference

GPT-6 Astra32.2%

GPT-5.4 mini13.4%

GDPval-AAOverall. Higher is better. No documented setup difference

GPT-6 Astra1,555.91 elo

GPT-5.4 mini1,011.97 elo

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-6 Astra and GPT-5.4 mini
Benchmark and task	GPT-6 Astra	GPT-5.4 mini	Source
AA-BriefcaseOverall Test details No documented difference in the test setupVersion: v1.1Metric: AA-Briefcase EloScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner1,546.7 elo	719.36 elo	Artificial Analysis Source details Data as of: 10/19/2026
AA-LCROverall Test details No documented difference in the test setupVersion: v1.1Metric: Pass rateScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner80.0%	77.0%	Artificial Analysis Source details Data as of: 10/19/2026
AA-OmniscienceOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: AA-Omniscience IndexScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner43.417 points The index can be negative and ranges from -100 to 100 according to Artificial Analysis.	-18.917 points The index can be negative and ranges from -100 to 100 according to Artificial Analysis.	Artificial Analysis Source details Data as of: 10/19/2026
AA-Omniscience AccuracyOverall Test details No documented difference in the test setupVersion: AA Omniscience diagnosticMetric: AA-Omniscience AccuracyScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: Xhigh, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboardGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.	Winner61.9% This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.	37.5% This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.	Artificial Analysis Source details Data as of: 10/19/2026
AA-Omniscience Hallucination RateOverall Test details No documented difference in the test setupVersion: AA Omniscience diagnosticMetric: AA-Omniscience Hallucination RateScoring: Lower is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: Xhigh, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboardGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).	Winner48.3% This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.	90.2% This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.	Artificial Analysis Source details Data as of: 10/19/2026
Artificial Analysis Intelligence IndexOverall Test details No documented difference in the test setupVersion: v4.3.2Metric: Artificial Analysis Intelligence IndexScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner52.386 points	24.068 points	Artificial Analysis Source details Data as of: 10/19/2026
AutomationBench-AAOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: Objectives completed without guardrail violationsScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner67.2%	26.2%	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value67.74 %	12.936 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value71.7 %	45.426 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value53.54 %	45.36 %	Vals AI Source details Data as of: 10/12/2026
GDP.pdfOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: All-pass rateScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner32.2%	13.4%	Artificial Analysis Source details Data as of: 10/19/2026
GDPval-AAOverall Test details No documented difference in the test setupVersion: v2.1Metric: GDPval-AA EloScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner1,555.91 elo	1,011.97 elo	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value5.417 %	0 %	Vals AI Source details Data as of: 10/12/2026
Humanity's Last ExamOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: Text-only pass@1 accuracyScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner54.6% Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.	28.1% Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value39.423 %	12.5 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.GPT-5.4 mini: Arena rating from 11,978 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.	1,397.568 95% confidence interval: ±6.522The 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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 11,674 published pairwise votes.GPT-5.4 mini: Arena rating from 63,461 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.	1,447.149 95% confidence interval: ±3.749The 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 Vision, 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 Vision, style control GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 3,590 published pairwise votes.GPT-5.4 mini: Arena rating from 25,733 published pairwise votes.	Higher measured value1,285.988 95% confidence interval: ±10.782The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,250.938 95% confidence interval: ±6.248The 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: 10/09/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: AA cohort: 1,730 questionsMetric: pass@1 accuracyScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh, Attempts: pass@1, one run per question GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: Xhigh, Attempts: pass@1, one run per questionGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.	Winner86.2% The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.	73.3% The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value5.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
SAGEOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 30,000 tokens	46.367 %	Higher measured value50.813 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value20.717 %	8.808 %	Vals AI Source details Data as of: 10/12/2026
Terminal-BenchOverall Test details No documented difference in the test setupVersion: 4.0Metric: Task successScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Xhigh), Reasoning: Xhigh GPT-5.4 mini: Snapshot: GPT-5.4 mini (Xhigh), Reasoning: XhighGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Xhigh) (release gpt-6-astra, row gpt-6-astra-xhigh, UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Xhigh) (release gpt-5-4-mini, row gpt-5-4-mini, UUID ba242e40-83b7-4cd3-a0e0-b56237984914, reasoning=true, source reasoning-token configuration budget=0, suffix=Xhigh). This configured value is not measured token consumption.	Winner59.6%	2.0%	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens	Higher measured value87.266 %	54.682 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value59.596 %	2.525 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value63.125 %	33.169 %	Vals AI Source details Data as of: 10/13/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Harness: OpenHands, Output limit: 128,000 tokens	Higher measured value89.594 %	47.969 %	Vals AI Source details Data as of: 10/12/2026
AA-Omniscience AccuracyOverall Test details No documented difference in the test setupVersion: AA Omniscience diagnosticMetric: AA-Omniscience AccuracyScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Medium), Reasoning: Medium, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard GPT-5.4 mini: Snapshot: GPT-5.4 mini (Medium), Reasoning: Medium, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboardGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Medium) (release gpt-6-astra, row gpt-6-astra-medium, UUID e97a4ef5-e817-480e-9595-12f81dc4974f, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Medium) (release gpt-5-4-mini, row gpt-5-4-mini-medium, UUID 392063ba-c3b5-47e8-ba67-a7b0b34f6824, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.	Winner60.6% This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.	36.5% This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.	Artificial Analysis Source details Data as of: 10/19/2026
AA-Omniscience Hallucination RateOverall Test details No documented difference in the test setupVersion: AA Omniscience diagnosticMetric: AA-Omniscience Hallucination RateScoring: Lower is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Medium), Reasoning: Medium, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard GPT-5.4 mini: Snapshot: GPT-5.4 mini (Medium), Reasoning: Medium, Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboardGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Medium) (release gpt-6-astra, row gpt-6-astra-medium, UUID e97a4ef5-e817-480e-9595-12f81dc4974f, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Medium) (release gpt-5-4-mini, row gpt-5-4-mini-medium, UUID 392063ba-c3b5-47e8-ba67-a7b0b34f6824, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).	Winner46.5% This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.	89.8% This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value67.463 %	8.2 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value77.953 %	40.488 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value48.318 %	45.366 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value88.768 %	52.536 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value53.03 %	15.152 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.GPT-5.4 mini: Arena rating from 11,978 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.	1,397.568 95% confidence interval: ±6.522The 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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,061 published pairwise votes.GPT-5.4 mini: Arena rating from 12,861 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.	1,459.776 95% confidence interval: ±6.483The 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 Vision, 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 Vision, style control GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 230 published pairwise votes.GPT-5.4 mini: Arena rating from 1,662 published pairwise votes.	Higher measured value1,357.126 95% confidence interval: ±39.572The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,285.423 95% confidence interval: ±17.385The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: AA cohort: 1,730 questionsMetric: pass@1 accuracyScoring: Higher is betterGPT-6 Astra: Snapshot: GPT-6 Astra (Medium), Reasoning: Medium, Attempts: pass@1, one run per question GPT-5.4 mini: Snapshot: GPT-5.4 mini (Medium), Reasoning: Medium, Attempts: pass@1, one run per questionGPT-6 Astra: Exact AA configuration: GPT-6 Astra (Medium) (release gpt-6-astra, row gpt-6-astra-medium, UUID e97a4ef5-e817-480e-9595-12f81dc4974f, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.GPT-5.4 mini: Exact AA configuration: GPT-5.4 mini (Medium) (release gpt-5-4-mini, row gpt-5-4-mini-medium, UUID 392063ba-c3b5-47e8-ba67-a7b0b34f6824, reasoning=true, source reasoning-token configuration budget=0, suffix=Medium). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.	Winner85.1% The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.	71.2% The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.	Artificial Analysis Source details Data as of: 10/19/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value50 %	3 %	Vals AI Source details Data as of: 10/12/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 30,000 tokens	37.302 %	Higher measured value41.27 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value13.333 %	3.333 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens	Higher measured value100 %	75 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value60 %	0 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value68.462 %	13.015 %	Vals AI Source details Data as of: 10/13/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value68.571 %	27.143 %	Vals AI Source details Data as of: 10/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value79.319 %	48.286 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value40.252 %	32.369 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value87.482 %	69.72 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 1,129 published pairwise votes.GPT-5.4 mini: Arena rating from 1,436 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.	1,419.865 95% confidence interval: ±16.676The 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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 877 published pairwise votes.GPT-5.4 mini: Arena rating from 3,925 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.	1,473.388 95% confidence interval: ±10.187The 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 Vision, Style ControlCreative writing vision 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 Vision, style control GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 367 published pairwise votes.GPT-5.4 mini: Arena rating from 1,627 published pairwise votes.	Higher measured value1,289.081 95% confidence interval: ±32.749The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,226.475 95% confidence interval: ±15.662The 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: 10/09/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value5.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
SAGECalculus Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 30,000 tokens	Higher measured value79.938 %	59.259 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value58.616 %	32.174 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens	Higher measured value87.778 %	34.444 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Media Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value66.667 %	0 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexEMB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value71.7 %	45.426 %	Vals AI Source details Data as of: 10/13/2026
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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value4.469 / 5	3.053 / 5	Vals AI Source details Data as of: 10/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value64.483 %	40.605 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	37.758 %	Higher measured value40.273 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value86.022 %	63.125 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens	Higher measured value32.558 %	11.628 %	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 GPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 3,422 published pairwise votes.GPT-5.4 mini: Arena rating from 9,859 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.	1,386.539 95% confidence interval: ±7.117The 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
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

GPT-5.4 mini

Unavailable in this round

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.

GPT-5.4 mini

Reasoning (requested): high

Current attempt

Run date: Oct 2, 2026
API provider: openrouter
Requested API model: openai/gpt-5.4-mini
API model reported in response: openai/gpt-5.4-mini
Reasoning setting: high
Pinned endpoint: OpenAI | openai/gpt-5.4-mini-20260317
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: 13.5 s

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

Earlier attempts (2)

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 GPT-5.4 mini with other leading models using the same data and benchmark logic.

View the complete LLM comparison

GPT-6 Astra vs. GPT-5.4 mini

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

GPT-6 Astra

GPT-5.4 mini

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons