Head-to-head comparison

Claude Fable 5.1 vs. Claude Fable 5

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

shared result series: 228
distinct benchmarks: 28
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 5.1 and Claude Fable 5
Attribute	Claude Fable 5.1	Claude Fable 5
Provider	Anthropic	Anthropic
Released	Sep 1, 2026	Jun 9, 2026
Availability	Active	Active
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,000,000 tokens	1,000,000 tokens
Knowledge cutoff	June 2026	January 2026
Technical sources	Model	Model, Context, Knowledge cutoff

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 5.1 and Claude Fable 5
Price type	Claude Fable 5.1	Claude Fable 5
API input	$10	$10
API output	$50	$50
Cache read	$0.25	$1
Cache write (5 min.)	$12.5	$12.5
Cache write (1 hr.)	$20	$20
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Fable 5.1Claude Fable 5

API inputUSD per 1M tokens, base tier

Claude Fable 5.1$10

Claude Fable 5$10

API outputUSD per 1M tokens, base tier

Claude Fable 5.1$50

Claude Fable 5$50

Cache readUSD per 1M tokens, base tier

Claude Fable 5.1$0.25

Claude Fable 5$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 5.1 and Claude Fable 5
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Fable 5.1	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	Source10/17/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
	Azure	Via OpenRouterazure	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
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	Source10/17/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
	Azure	Via OpenRouterazure	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
	Claude Platform on AWS	Via OpenRouterclaude-on-aws	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/europe	$11	$55	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $10	Lowest listed price: $50	Source10/17/2026

Performance

Shared benchmarks

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

Capability profile from matched benchmarks

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

Claude Fable 5.1

Claude Fable 5

Coding: 99.3 / 82.8 (5 benchmark families)

Reasoning: 100 / 99.7 (1 benchmark family)

Mathematics: 100 / 95 (1 benchmark family)

Knowledge: 99.9 / 99 (1 benchmark family)

Finance: 99.7 / 93.9 (5 benchmark families)

Legal: 93.5 / 96.4 (3 benchmark families)

Agentic tasks: 100 / 77 (1 benchmark family)

Multimodal: 100 / 98.5 (1 benchmark family)

178 matched rows from 22 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Claude Fable 5.1Claude Fable 5

Code MigrationOverall. Higher is better. No documented setup difference

Claude Fable 5.154.607 %

Claude Fable 555.065 %

EMBOverall. Higher is better. No documented setup difference

Claude Fable 5.176.67 %

Claude Fable 573.666 %

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

Claude Fable 5.158.877 %

Claude Fable 556.314 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Claude Fable 5.193.434 %

Claude Fable 593.182 %

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

Claude Fable 5.16.667 %

Claude Fable 511.25 %

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

Claude Fable 5.155.288 %

Claude Fable 549.519 %

LegalBenchOverall. Higher is better. No documented setup difference

Claude Fable 5.188.511 %

Claude Fable 588.561 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Claude Fable 5.190.515 %

Claude Fable 589.778 %

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

Claude Fable 5.11,742.652

Claude Fable 51,623.828

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

Claude Fable 5.11,500.568

Claude Fable 51,503.377

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

Claude Fable 5.11,286.407

Claude Fable 51,307.966

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

Claude Fable 5.153.509 %

Claude Fable 556.07 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Fable 5.1 and Claude Fable 5
Benchmark and task	Claude Fable 5.1	Claude Fable 5	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	54.607 %	Winner55.065 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner76.67 %	73.666 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner58.877 %	56.314 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner93.434 %	93.182 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	6.667 %	Winner11.25 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner55.288 %	49.519 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	88.511 %	Winner88.561 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner90.515 %	89.778 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Fable 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Code Arena WebDev Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Fable 5.1: Arena rating from 7,230 published pairwise votes.Claude Fable 5: Arena rating from 15,295 published pairwise votes.	Higher measured value1,742.652 95% confidence interval: ±9.147The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,623.828 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Text, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style controlClaude Fable 5.1: Arena rating from 14,121 published pairwise votes.Claude Fable 5: Arena rating from 41,439 published pairwise votes.	1,500.568 95% confidence interval: ±6.106The 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 value1,503.377 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Vision, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style controlClaude Fable 5.1: Arena rating from 4,648 published pairwise votes.Claude Fable 5: Arena rating from 14,175 published pairwise votes.	1,286.407 95% confidence interval: ±9.66The 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 value1,307.966 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.	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 5.1: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens	53.509 %	Higher measured value56.07 %	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 5.1: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens	Higher measured value91.294 %	88.522 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner92.375 %	91.502 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner90.636 %	89.306 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner70.786 %	68.919 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchOverall Test details No documented difference in the test setupVersion: 1Metric: fully resolved rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner7 %	2 %	Vals AI Source details Data as of: 10/12/2026
ProofBenchOverall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner100 %	95 %	Vals AI Source details Data as of: 10/12/2026
Public Benefits Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner74.899 %	70.433 %	Vals AI Source details Data as of: 10/12/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 30,000 tokens	48.526 %	Winner51.89 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner49.194 %	38.281 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	75.961 %	Winner76.942 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Fable 5.1: Compute: high, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Higher measured value85.019 %	80.524 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Overall Test details No documented difference in the test setupVersion: 4.0Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner58.081 %	41.414 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: trial pass rateScoring: Higher is betterClaude Fable 5.1: Reasoning: high, Agent: Claude Code, Attempts: 330 graded trials Claude Fable 5: Reasoning: max, Agent: Claude Code, Attempts: 330 graded trialsClaude Fable 5.1: 330 graded trials, Claude Code agent, high reasoning. Dataset version 1922072f-a433-429a-8929-350d5e1bcf02.Claude Fable 5: 330 graded trials, Claude Code agent, max reasoning. Dataset version 1922072f-a433-429a-8929-350d5e1bcf02.	Higher measured value54.55 % Selection of exactly identified models from the official 35-row leaderboard. Agents and reasoning efforts differ. These values do not belong to the separate Vals Mini-SWE-agent cohort.	44.55 % 95% confidence interval: ±3.85Selection of exactly identified models from the official 35-row leaderboard. Agents and reasoning efforts differ. These values do not belong to the separate Vals Mini-SWE-agent cohort.	Terminal-Bench Source details Data as of: 10/06/2026
Terminal-Bench ScienceOverall Test details No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens	Winner40 %	15.714 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2.1Metric: weighted index scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner65.827 %	61.388 %	Vals AI Source details Data as of: 10/13/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens	90.263 %	Winner90.352 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	52.809 %	Winner60.087 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner82.233 %	70.785 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner54.393 %	51.092 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondFew-Shot CoT Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Tie92.929 %	Tie92.929 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details No documented difference in the test setupVersion: 1Metric: criteria pass rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	89.855 %	Winner92.035 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner68.182 %	57.576 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchConclusion Tasks Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner92.511 %	91.775 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Easy Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner99.068 %	98.758 %	Vals AI Source details Data as of: 09/01/2026
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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Code Arena WebDev Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Fable 5.1: Arena rating from 2,470 published pairwise votes.Claude Fable 5: Arena rating from 5,457 published pairwise votes.	Higher measured value1,719.751 95% confidence interval: ±13.642The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,622.483 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Text, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style controlClaude Fable 5.1: Arena rating from 2,589 published pairwise votes.Claude Fable 5: Arena rating from 8,265 published pairwise votes.	1,485.231 95% confidence interval: ±11.847The 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 value1,501.237 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Vision, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style controlClaude Fable 5.1: Arena rating from 260 published pairwise votes.Claude Fable 5: Arena rating from 765 published pairwise votes.	1,340.8 95% confidence interval: ±36.169The 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 value1,355.183 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.	LMArena Source details Data as of: 10/09/2026
MMLU-ProBiology Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner96.095 %	93.584 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxNumerical Extraction Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner77.583 %	76.709 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchAlmost Resolved Test details No documented difference in the test setupVersion: 1Metric: almost-resolved rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner53.5 %	33 %	Vals AI Source details Data as of: 10/12/2026
SAGEAutomata Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 30,000 tokens	34.524 %	Winner39.682 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchControversy & Precedence Analysis Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner26.667 %	13.333 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Correctness Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	64.105 %	Winner65.822 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Fable 5.1: Compute: high, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, 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 No documented difference in the test setupVersion: 4.0Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner60 %	40 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench 4.0Overall Test details No documented difference in the test setupVersion: 4.0Metric: trial pass rateScoring: Higher is betterSettings: Reasoning: max, Agent: Claude Code, Attempts: 330 graded trials330 graded trials, Claude Code agent, max reasoning. Dataset version 1922072f-a433-429a-8929-350d5e1bcf02.	Winner57.88 % 95% confidence interval: ±3.76Selection of exactly identified models from the official 35-row leaderboard. Agents and reasoning efforts differ. These values do not belong to the separate Vals Mini-SWE-agent cohort.	44.55 % 95% confidence interval: ±3.85Selection of exactly identified models from the official 35-row leaderboard. Agents and reasoning efforts differ. These values do not belong to the separate Vals Mini-SWE-agent cohort.	Terminal-Bench Source details Data as of: 10/06/2026
Terminal-Bench ScienceEarth Sciences Test details No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens	Tie25 %	Tie25 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexCode Migration Test details No documented difference in the test setupVersion: 2.1Metric: benchmark scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner60.033 %	54.635 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCOBOL Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner60 %	40 %	Vals AI Source details Data as of: 10/12/2026
EMBDataroom Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner86.736 %	85.362 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner47.773 %	45.694 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondZero-Shot CoT Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner93.939 %	93.434 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Tie0 %	Tie0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details No documented difference in the test setupVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner92.519 %	90.224 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchInterpretation Tasks Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner86.902 %	86.863 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Hard Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner80.571 %	79.714 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Fable 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Code Arena WebDev Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Code Arena WebDevClaude Fable 5.1: Arena rating from 7,230 published pairwise votes.Claude Fable 5: Arena rating from 15,295 published pairwise votes.	Higher measured value1,742.652 95% confidence interval: ±9.147The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,623.828 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Text, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Text, style controlClaude Fable 5.1: Arena rating from 1,069 published pairwise votes.Claude Fable 5: Arena rating from 3,073 published pairwise votes.	Higher measured value1,567.304 95% confidence interval: ±18.995The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,554.631 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.	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 5.1: Snapshot: claude-fable-5.1-max, Reasoning: max, Harness: Arena Vision, style control Claude Fable 5: Snapshot: claude-fable-5-high, Reasoning: high, Harness: Arena Vision, style controlClaude Fable 5.1: Arena rating from 476 published pairwise votes.Claude Fable 5: Arena rating from 1,115 published pairwise votes.	1,289.586 95% confidence interval: ±29.623The 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 value1,320.194 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.	LMArena Source details Data as of: 10/09/2026
MMLU-ProBusiness Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner95.184 %	93.156 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxSemantic Extraction Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner63.99 %	61.129 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchFully Resolved Test details No documented difference in the test setupVersion: 1Metric: fully resolved rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens	Winner7 %	2 %	Vals AI Source details Data as of: 10/12/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

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

Shared test round: 4ae5d8eeb9a9

Claude Fable 5.1

Unavailable in this round

Claude Fable 5

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Fable 5.1

Reasoning (requested): high

Current attempt

Run date: Sep 7, 2026
API provider: openrouter
Requested API model: anthropic/claude-fable-5.1
API model reported in response: anthropic/claude-fable-5.1
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-fable-5.1-20260831
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: 27 s

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

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.

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

View the complete LLM comparison

Claude Fable 5.1 vs. Claude Fable 5

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Fable 5.1

Claude Fable 5

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons