Head-to-head comparison

Claude Fable 5 vs. GPT-6 Astra

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

shared result series: 189
distinct benchmark metrics: 20
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 Claude Fable 5 and GPT-6 Astra
Attribute	Claude Fable 5	GPT-6 Astra
Provider	Anthropic	OpenAI
Released	Jun 9, 2026	Sep 3, 2026
Availability	Active	Limited access
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,000,000 tokens	1,050,000 tokens
Knowledge cutoff	January 2026	April 30, 2026
Technical sources	Model, Context, Knowledge cutoff	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 Claude Fable 5 and GPT-6 Astra
Price type	Claude Fable 5	GPT-6 Astra
API input	$10	$10 ≤272K / $20 >272K
API output	$50	$50 ≤272K / $75 >272K
Cache read	$1	$1 ≤272K / $2 >272K
Cache write (5 min.)	$12.5	$12.5 ≤272K / $25 >272K
Cache write (1 hr.)	$20	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Fable 5GPT-6 Astra

API inputUSD per 1M tokens, base tier

Claude Fable 5$10

GPT-6 Astra$10

API outputUSD per 1M tokens, base tier

Claude Fable 5$50

GPT-6 Astra$50

Cache readUSD per 1M tokens, base tier

Claude Fable 5$1

GPT-6 Astra$1

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

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

Provider pricing for Claude Fable 5 and GPT-6 Astra
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Fable 5	Anthropic	Direct from developerStandard API	Lowest listed price: $10	Lowest listed price: $50	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock	Lowest listed price: $10	Lowest listed price: $50	Source10/19/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $10	Lowest listed price: $50	Source10/19/2026
	Azure	Via OpenRouterazure	Lowest listed price: $10	Lowest listed price: $50	Source10/19/2026
	Claude Platform on AWS	Via OpenRouterclaude-on-aws	Lowest listed price: $10	Lowest listed price: $50	Source10/19/2026
	Google	Via OpenRoutergoogle-vertex/europe	$11	$55	Source10/19/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $10	Lowest listed price: $50	Source10/19/2026
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

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.

Claude Fable 5GPT-6 Astra

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

Claude Fable 555.065 %

GPT-6 Astra67.74 %

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

Claude Fable 573.666 %

GPT-6 Astra71.7 %

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

Claude Fable 556.314 %

GPT-6 Astra53.54 %

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

Claude Fable 511.25 %

GPT-6 Astra5.417 %

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

Claude Fable 549.519 %

GPT-6 Astra39.423 %

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

Claude Fable 51,623.828

GPT-6 Astra1,780.244

LMArena SearchOverall. Higher is better. Test setup not documented as identical

Claude Fable 51,229.14

GPT-6 Astra1,233.616

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

Claude Fable 51,503.377

GPT-6 Astra1,476.716

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

Claude Fable 51,307.966

GPT-6 Astra1,285.988

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

Claude Fable 556.07 %

GPT-6 Astra48.486 %

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

Claude Fable 588.522 %

GPT-6 Astra87.908 %

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

Claude Fable 52 %

GPT-6 Astra5.5 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Fable 5 and GPT-6 Astra
Benchmark and task	Claude Fable 5	GPT-6 Astra	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	55.065 %	Higher measured value67.74 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value73.666 %	71.7 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value56.314 %	53.54 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value11.25 %	5.417 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value49.519 %	39.423 %	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDev GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Fable 5: Arena rating from 15,295 published pairwise votes.GPT-6 Astra: Arena rating from 5,746 published pairwise votes.	1,623.828 95% confidence interval: ±6.238The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	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.	LMArena Source details Data as of: 10/13/2026
LMArena SearchOverall Test details Test setup not documented as identicalNo direct winnerVersion: searchMetric: Search Arena Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Search GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena SearchClaude Fable 5: Arena rating from 73,596 published pairwise votes.GPT-6 Astra: Arena rating from 18,483 published pairwise votes.	1,229.14 95% confidence interval: ±6.51The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,233.616 95% confidence interval: ±7.842The 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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style controlClaude Fable 5: Arena rating from 41,439 published pairwise votes.GPT-6 Astra: Arena rating from 11,674 published pairwise votes.	Higher measured value1,503.377 95% confidence interval: ±4.304The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,476.716 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.	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style controlClaude Fable 5: Arena rating from 14,175 published pairwise votes.GPT-6 Astra: Arena rating from 3,590 published pairwise votes.	Higher measured value1,307.966 95% confidence interval: ±7.156The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,285.988 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.	LMArena Source details Data as of: 10/09/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value56.07 %	48.486 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value88.522 %	87.908 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	2 %	Higher measured value5.5 %	Vals AI Source details Data as of: 10/12/2026
ProofBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	95 %	Higher measured value99 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens	Higher measured value51.89 %	46.367 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value38.281 %	20.717 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	80.524 %	Higher measured value87.266 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	41.414 %	Higher measured value59.596 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceOverall Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens	15.714 %	Higher measured value62.857 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	61.388 %	Higher measured value63.125 %	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 betterClaude Fable 5: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens	Higher measured value90.352 %	89.594 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	60.087 %	Higher measured value67.463 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	70.785 %	Higher measured value77.953 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value51.092 %	48.318 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value92.035 %	88.768 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value57.576 %	53.03 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevImage to webdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDev GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Fable 5: Arena rating from 5,457 published pairwise votes.GPT-6 Astra: Arena rating from 2,739 published pairwise votes.	1,622.483 95% confidence interval: ±9.201The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,731.395 95% confidence interval: ±13.296The 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
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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style controlClaude Fable 5: Arena rating from 8,265 published pairwise votes.GPT-6 Astra: Arena rating from 2,061 published pairwise votes.	Higher measured value1,501.237 95% confidence interval: ±7.279The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,472.34 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.	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style controlClaude Fable 5: Arena rating from 765 published pairwise votes.GPT-6 Astra: Arena rating from 230 published pairwise votes.	1,355.183 95% confidence interval: ±23.131The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	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.	LMArena Source details Data as of: 10/09/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	33 %	Higher measured value50 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens	Higher measured value39.682 %	37.302 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	No direct winner13.333 %	No direct winner13.333 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	No direct winner100 %	No direct winner100 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	40 %	Higher measured value60 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEarth Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens	25 %	Higher measured value62.5 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	54.635 %	Higher measured value68.462 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	40 %	Higher measured value68.571 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value85.362 %	79.319 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value45.694 %	40.252 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, 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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value90.224 %	87.482 %	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDev GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Fable 5: Arena rating from 15,295 published pairwise votes.GPT-6 Astra: Arena rating from 5,746 published pairwise votes.	1,623.828 95% confidence interval: ±6.238The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	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.	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style controlClaude Fable 5: Arena rating from 3,073 published pairwise votes.GPT-6 Astra: Arena rating from 877 published pairwise votes.	Higher measured value1,554.631 95% confidence interval: ±11.32The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,514.537 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.	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style controlClaude Fable 5: Arena rating from 1,115 published pairwise votes.GPT-6 Astra: Arena rating from 367 published pairwise votes.	Higher measured value1,320.194 95% confidence interval: ±18.881The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,289.081 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.	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	2 %	Higher measured value5.5 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens	Higher measured value82.407 %	79.938 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value68.433 %	58.616 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	70 %	Higher measured value87.778 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	50 %	Higher measured value66.667 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEngineering Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens	0 %	Higher measured value33.333 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexEMB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value73.666 %	71.7 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	4.442 / 5	Higher measured value4.469 / 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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value68.865 %	64.483 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value43.986 %	37.758 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value91.398 %	86.022 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value51.163 %	32.558 %	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDev GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Fable 5: Arena rating from 2,090 published pairwise votes.GPT-6 Astra: Arena rating from 1,129 published pairwise votes.	1,650.179 95% confidence interval: ±14.96The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	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.	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 betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style controlClaude Fable 5: Arena rating from 10,745 published pairwise votes.GPT-6 Astra: Arena rating from 2,659 published pairwise votes.	Higher measured value1,550.53 95% confidence interval: ±6.633The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,543.161 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.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlDiagram Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style control GPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style controlClaude Fable 5: Arena rating from 3,815 published pairwise votes.GPT-6 Astra: Arena rating from 861 published pairwise votes.	Higher measured value1,351.186 95% confidence interval: ±10.539The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,310.509 95% confidence interval: ±20.739The 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
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: raw test pass rateScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	76.803 %	Higher measured value85.417 %	Vals AI Source details Data as of: 10/12/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens	Higher measured value71.544 %	62.117 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	Higher measured value53.169 %	29.944 %	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 betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	84.848 %	Higher measured value86.061 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0ML Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Output limit: 128,000 tokens	42.424 %	Higher measured value66.667 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceLife Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Fable 5: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens GPT-6 Astra: Reasoning: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens	10.526 %	Higher measured value68.421 %	Vals AI Source details Data as of: 10/14/2026
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

Claude Fable 5

Unavailable in this round

GPT-6 Astra

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Fable 5

Reasoning (requested): high

Current attempt

Run date: Sep 7, 2026
API provider: openrouter
Requested API model: anthropic/claude-fable-5
API model reported in response: anthropic/claude-fable-5
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-5-fable-20260609
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: 53.1 s

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

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.

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 Claude Fable 5 and GPT-6 Astra with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Fable 5 vs. GPT-6 Astra

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Fable 5

GPT-6 Astra

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons