Model profile · Anthropic

Claude Fable 5

Closed weightsfrontier · registry tag 2026 flagship

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 31.5%
Verified coverage: 31.5%
Spread: 96.4%
Last verified: Jun 20, 2026

86%bench fit

textcodevisiondocument4 aliases31 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text25 benchmarks87.2%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

100% percentile inside its fair comparison set

60Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

100% percentile inside its fair comparison set

61.4%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #41 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 86.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

86.6% percentile inside its fair comparison set

45.1%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #49 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 63.5%
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

84.8% percentile inside its fair comparison set

63.5%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #267 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $20 /1M tokens
Percentile: 3.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

3.6% percentile inside its fair comparison set

$20 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #266 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M input tokens
Percentile: 4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

4% percentile inside its fair comparison set

$10 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #267 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $50 /1M output tokens
Percentile: 3.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

3.6% percentile inside its fair comparison set

$50 /1M output tokensRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 4297. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,498 - 1,517

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: creative_writing. Source rank: #1. Votes: 782. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,479 - 1,522

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,514
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #2. Votes: 2107. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,514Raw benchmark valueCI 1,501 - 1,526

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: exclude_ties. Source rank: #1. Votes: 3212. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,517 - 1,543

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,531
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts. Source rank: #2. Votes: 2673. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,531Raw benchmark valueCI 1,520 - 1,543

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,528
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts_english. Source rank: #3. Votes: 1379. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,528Raw benchmark valueCI 1,512 - 1,544

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: instruction_following. Source rank: #1. Votes: 1426. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,501 - 1,533

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: longer_query. Source rank: #2. Votes: 1787. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,508 - 1,538

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: multi_turn. Source rank: #1. Votes: 730. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,502 - 1,548

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #3. Votes: 4297. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,484 - 1,503

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: creative_writing. Source rank: #2. Votes: 782. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,468 - 1,512

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #3. Votes: 2107. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,485 - 1,511

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: exclude_ties. Source rank: #3. Votes: 3212. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,496 - 1,521

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts. Source rank: #3. Votes: 2673. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,497 - 1,521

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts_english. Source rank: #3. Votes: 1379. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,489 - 1,521

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: instruction_following. Source rank: #3. Votes: 1426. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,493 - 1,526

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: longer_query. Source rank: #3. Votes: 1787. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,496 - 1,525

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: multi_turn. Source rank: #1. Votes: 730. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,488 - 1,534

Coding17 benchmarks100%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.9%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

100% percentile inside its fair comparison set

62.9%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

100% percentile inside its fair comparison set

60.2%Raw benchmark value

Coding Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

100% percentile inside its fair comparison set

76Raw benchmark value

Agentic Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

100% percentile inside its fair comparison set

53Raw benchmark value

Code Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,654
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 2095. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,654Raw benchmark valueCI 1,638 - 1,669

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,654
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev. Source rank: #1. Votes: 2095. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,654Raw benchmark valueCI 1,638 - 1,669

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,664
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev-html. Source rank: #1. Votes: 301. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,664Raw benchmark valueCI 1,623 - 1,705

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,646
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev-react. Source rank: #1. Votes: 1794. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,646Raw benchmark valueCI 1,629 - 1,662

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Anthropic.

100% percentile inside its fair comparison set

55.1%Raw benchmark valueCI 46% - 64.1%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Anthropic.

100% percentile inside its fair comparison set

89.8%Raw benchmark valueCI 88% - 91.5%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Anthropic.

100% percentile inside its fair comparison set

2%Raw benchmark valueCI 0.1% - 3.9%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 95%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Anthropic.

100% percentile inside its fair comparison set

95%Raw benchmark valueCI 93.1% - 96.9%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

100% percentile inside its fair comparison set

80.5%Raw benchmark valueCI 77.9% - 83.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Anthropic.

100% percentile inside its fair comparison set

90.4%Raw benchmark valueCI 86.2% - 94.5%

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: coding. Source rank: #1. Votes: 1126. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,545 - 1,582

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: coding. Source rank: #3. Votes: 1126. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,512 - 1,549

IOI

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: Anthropic.

100% percentile inside its fair comparison set

72.3%Raw benchmark valueCI 53.9% - 90.6%

Reasoning / math / science8 benchmarks99.6%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

100% percentile inside its fair comparison set

53.3%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 92.6%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.5% percentile inside its fair comparison set

92.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.6%
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

99.3% percentile inside its fair comparison set

28.6%Raw benchmark value

ProofBench

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Anthropic.

100% percentile inside its fair comparison set

77%Raw benchmark valueCI 68.7% - 85.3%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.2%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Anthropic.

98.9% percentile inside its fair comparison set

93.2%Raw benchmark valueCI 89.4% - 97%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Anthropic.

100% percentile inside its fair comparison set

91.5%Raw benchmark valueCI 91% - 92%

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: math. Source rank: #1. Votes: 244. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,480 - 1,554

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,513
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: math. Source rank: #3. Votes: 244. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,513Raw benchmark valueCI 1,475 - 1,551

Professional reasoning28 benchmarks98.9%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,771
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

100% percentile inside its fair comparison set

1,771Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Anthropic.

100% percentile inside its fair comparison set

75Raw benchmark valueCI 74 - 76

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: Anthropic.

100% percentile inside its fair comparison set

11.3%Raw benchmark valueCI 7% - 15.5%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Anthropic.

100% percentile inside its fair comparison set

88.6%Raw benchmark valueCI 87.9% - 89.2%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.3%
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Anthropic.

96% percentile inside its fair comparison set

56.3%Raw benchmark valueCI 54.7% - 58%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #3 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.9%
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

97.8% percentile inside its fair comparison set

76.9%Raw benchmark valueCI 75.3% - 78.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.1%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Anthropic.

98% percentile inside its fair comparison set

56.1%Raw benchmark valueCI 51.8% - 60.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Anthropic.

100% percentile inside its fair comparison set

88.5%Raw benchmark valueCI 84.7% - 92.3%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: expert. Source rank: #3. Votes: 434. Organization: anthropic. License: Proprietary.

99.6% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,507 - 1,564

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_business_and_management_and_financial_operations. Source rank: #2. Votes: 906. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,482 - 1,522

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_entertainment_and_sports_and_media. Source rank: #2. Votes: 1014. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,471 - 1,509

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_legal_and_government. Source rank: #1. Votes: 329. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,491 - 1,555

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_life_and_physical_and_social_science. Source rank: #4. Votes: 727. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,495 - 1,540

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_mathematical. Source rank: #2. Votes: 242. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,479 - 1,554

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_medicine_and_healthcare. Source rank: #12. Votes: 302. Organization: anthropic. License: Proprietary.

96.9% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,464 - 1,533

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1587. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,528 - 1,559

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1146. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,497 - 1,533

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: expert. Source rank: #3. Votes: 434. Organization: anthropic. License: Proprietary.

99.6% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,492 - 1,548

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_business_and_management_and_financial_operations. Source rank: #4. Votes: 906. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,461 - 1,501

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_entertainment_and_sports_and_media. Source rank: #3. Votes: 1014. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,457 - 1,495

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_legal_and_government. Source rank: #3. Votes: 329. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,477 - 1,542

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_life_and_physical_and_social_science. Source rank: #8. Votes: 727. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,473 - 1,517

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_mathematical. Source rank: #4. Votes: 242. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,472 - 1,548

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #16

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_medicine_and_healthcare. Source rank: #19. Votes: 302. Organization: anthropic. License: Proprietary.

94.9% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,435 - 1,503

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_software_and_it_services. Source rank: #3. Votes: 1587. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,502 - 1,532

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1146. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,487 - 1,524

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #5 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.9%
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Anthropic.

91.1% percentile inside its fair comparison set

51.9%Raw benchmark valueCI 45.2% - 58.6%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench-v1; provider: Anthropic.

100% percentile inside its fair comparison set

71.7%Raw benchmark valueCI 69.4% - 73.9%

Search / tool use3 benchmarks97.6%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #6 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 98.5%
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

99.4% percentile inside its fair comparison set

98.5%Raw benchmark value

Search Arena

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 5007. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,228 - 1,249

Search Arena · No Style Control

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #3. Votes: 5007. Organization: anthropic. License: Proprietary.

93.3% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,227 - 1,248

Long context2 benchmarks99.4%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #5 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 70%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

98.7% percentile inside its fair comparison set

70%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Anthropic.

100% percentile inside its fair comparison set

71.8%Raw benchmark valueCI 70.1% - 73.6%

Vision understanding11 benchmarks99.5%

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,307
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #2. Votes: 1785. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,307Raw benchmark valueCI 1,292 - 1,323

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: diagram. Source rank: #1. Votes: 497. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,315 - 1,371

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #3. Votes: 840. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,281 - 1,324

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,335
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: homework. Source rank: #2. Votes: 286. Organization: anthropic. License: Proprietary.

98.5% percentile inside its fair comparison set

1,335Raw benchmark valueCI 1,299 - 1,371

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: ocr. Source rank: #1. Votes: 1342. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,306 - 1,340

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 1785. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,308 - 1,338

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: diagram. Source rank: #1. Votes: 497. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,319 - 1,375

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #4. Votes: 840. Organization: anthropic. License: Proprietary.

98.2% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,300 - 1,343

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,345
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: homework. Source rank: #1. Votes: 286. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,345Raw benchmark valueCI 1,308 - 1,381

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: ocr. Source rank: #1. Votes: 1342. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,317 - 1,351

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Anthropic.

100% percentile inside its fair comparison set

89.3%Raw benchmark valueCI 87.8% - 90.8%

Document understanding4 benchmarks96.2%

Document Arena

AR · Document understanding · Human

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 1461. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,485 - 1,515

Document Arena · No Style Control

AR · Document understanding · Human

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #5. Votes: 1461. Organization: anthropic. License: Proprietary.

91.7% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,480 - 1,510

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: Anthropic.

100% percentile inside its fair comparison set

74Raw benchmark valueCI 73 - 75

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #5 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.9%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Anthropic.

93.3% percentile inside its fair comparison set

68.9%Raw benchmark valueCI 67.1% - 70.7%

Multilingual4 benchmarks99.5%

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: french. Source rank: #3. Votes: 193. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,478 - 1,570

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: russian. Source rank: #1. Votes: 382. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,502 - 1,564

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: french. Source rank: #3. Votes: 193. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,458 - 1,549

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: russian. Source rank: #1. Votes: 382. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,488 - 1,550

Source links and registry checks

official

Anthropic model overview

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

Model profile · Anthropic

Claude Fable 5

Closed weightsfrontier · registry tag 2026 flagship

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 31.5%
Verified coverage: 31.5%
Spread: 96.4%
Last verified: Jun 20, 2026

86%bench fit

textcodevisiondocument4 aliases31 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text25 benchmarks87.2%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

100% percentile inside its fair comparison set

60Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

100% percentile inside its fair comparison set

61.4%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #41 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.1%
Percentile: 86.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

86.6% percentile inside its fair comparison set

45.1%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #49 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 63.5%
Percentile: 84.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

84.8% percentile inside its fair comparison set

63.5%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #267 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $20 /1M tokens
Percentile: 3.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

3.6% percentile inside its fair comparison set

$20 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #266 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M input tokens
Percentile: 4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

4% percentile inside its fair comparison set

$10 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #267 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $50 /1M output tokens
Percentile: 3.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

3.6% percentile inside its fair comparison set

$50 /1M output tokensRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 4297. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,498 - 1,517

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: creative_writing. Source rank: #1. Votes: 782. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,479 - 1,522

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,514
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #2. Votes: 2107. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,514Raw benchmark valueCI 1,501 - 1,526

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: exclude_ties. Source rank: #1. Votes: 3212. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,517 - 1,543

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,531
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts. Source rank: #2. Votes: 2673. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,531Raw benchmark valueCI 1,520 - 1,543

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,528
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts_english. Source rank: #3. Votes: 1379. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,528Raw benchmark valueCI 1,512 - 1,544

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: instruction_following. Source rank: #1. Votes: 1426. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,501 - 1,533

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: longer_query. Source rank: #2. Votes: 1787. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,508 - 1,538

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: multi_turn. Source rank: #1. Votes: 730. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,502 - 1,548

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #3. Votes: 4297. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,484 - 1,503

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: creative_writing. Source rank: #2. Votes: 782. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,468 - 1,512

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #3. Votes: 2107. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,485 - 1,511

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: exclude_ties. Source rank: #3. Votes: 3212. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,496 - 1,521

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts. Source rank: #3. Votes: 2673. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,497 - 1,521

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: hard_prompts_english. Source rank: #3. Votes: 1379. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,489 - 1,521

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: instruction_following. Source rank: #3. Votes: 1426. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,493 - 1,526

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: longer_query. Source rank: #3. Votes: 1787. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,496 - 1,525

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: multi_turn. Source rank: #1. Votes: 730. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,488 - 1,534

Coding17 benchmarks100%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.9%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

100% percentile inside its fair comparison set

62.9%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 60.2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

100% percentile inside its fair comparison set

60.2%Raw benchmark value

Coding Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

100% percentile inside its fair comparison set

76Raw benchmark value

Agentic Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

100% percentile inside its fair comparison set

53Raw benchmark value

Code Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,654
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 2095. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,654Raw benchmark valueCI 1,638 - 1,669

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,654
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev. Source rank: #1. Votes: 2095. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,654Raw benchmark valueCI 1,638 - 1,669

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,664
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev-html. Source rank: #1. Votes: 301. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,664Raw benchmark valueCI 1,623 - 1,705

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,646
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: webdev-react. Source rank: #1. Votes: 1794. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,646Raw benchmark valueCI 1,629 - 1,662

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Anthropic.

100% percentile inside its fair comparison set

55.1%Raw benchmark valueCI 46% - 64.1%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Anthropic.

100% percentile inside its fair comparison set

89.8%Raw benchmark valueCI 88% - 91.5%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Anthropic.

100% percentile inside its fair comparison set

2%Raw benchmark valueCI 0.1% - 3.9%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 95%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Anthropic.

100% percentile inside its fair comparison set

95%Raw benchmark valueCI 93.1% - 96.9%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Anthropic.

100% percentile inside its fair comparison set

80.5%Raw benchmark valueCI 77.9% - 83.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Anthropic.

100% percentile inside its fair comparison set

90.4%Raw benchmark valueCI 86.2% - 94.5%

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: coding. Source rank: #1. Votes: 1126. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,545 - 1,582

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: coding. Source rank: #3. Votes: 1126. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,512 - 1,549

IOI

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: Anthropic.

100% percentile inside its fair comparison set

72.3%Raw benchmark valueCI 53.9% - 90.6%

Reasoning / math / science8 benchmarks99.6%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

100% percentile inside its fair comparison set

53.3%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 92.6%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.5% percentile inside its fair comparison set

92.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 28.6%
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

99.3% percentile inside its fair comparison set

28.6%Raw benchmark value

ProofBench

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Anthropic.

100% percentile inside its fair comparison set

77%Raw benchmark valueCI 68.7% - 85.3%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.2%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Anthropic.

98.9% percentile inside its fair comparison set

93.2%Raw benchmark valueCI 89.4% - 97%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Anthropic.

100% percentile inside its fair comparison set

91.5%Raw benchmark valueCI 91% - 92%

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: math. Source rank: #1. Votes: 244. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,480 - 1,554

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,513
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: math. Source rank: #3. Votes: 244. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,513Raw benchmark valueCI 1,475 - 1,551

Professional reasoning28 benchmarks98.9%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #1 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,771
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

100% percentile inside its fair comparison set

1,771Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Anthropic.

100% percentile inside its fair comparison set

75Raw benchmark valueCI 74 - 76

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: Anthropic.

100% percentile inside its fair comparison set

11.3%Raw benchmark valueCI 7% - 15.5%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Anthropic.

100% percentile inside its fair comparison set

88.6%Raw benchmark valueCI 87.9% - 89.2%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.3%
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Anthropic.

96% percentile inside its fair comparison set

56.3%Raw benchmark valueCI 54.7% - 58%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #3 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 76.9%
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Anthropic.

97.8% percentile inside its fair comparison set

76.9%Raw benchmark valueCI 75.3% - 78.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #2 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.1%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Anthropic.

98% percentile inside its fair comparison set

56.1%Raw benchmark valueCI 51.8% - 60.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.5%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Anthropic.

100% percentile inside its fair comparison set

88.5%Raw benchmark valueCI 84.7% - 92.3%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: expert. Source rank: #3. Votes: 434. Organization: anthropic. License: Proprietary.

99.6% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,507 - 1,564

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

99.7% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,482 - 1,522

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_entertainment_and_sports_and_media. Source rank: #2. Votes: 1014. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,471 - 1,509

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_legal_and_government. Source rank: #1. Votes: 329. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,491 - 1,555

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_life_and_physical_and_social_science. Source rank: #4. Votes: 727. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,495 - 1,540

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_mathematical. Source rank: #2. Votes: 242. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,479 - 1,554

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_medicine_and_healthcare. Source rank: #12. Votes: 302. Organization: anthropic. License: Proprietary.

96.9% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,464 - 1,533

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1587. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,528 - 1,559

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1146. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,497 - 1,533

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: expert. Source rank: #3. Votes: 434. Organization: anthropic. License: Proprietary.

99.6% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,492 - 1,548

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

99.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,461 - 1,501

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_entertainment_and_sports_and_media. Source rank: #3. Votes: 1014. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,457 - 1,495

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_legal_and_government. Source rank: #3. Votes: 329. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,477 - 1,542

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_life_and_physical_and_social_science. Source rank: #8. Votes: 727. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,473 - 1,517

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_mathematical. Source rank: #4. Votes: 242. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,472 - 1,548

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #16

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,469
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_medicine_and_healthcare. Source rank: #19. Votes: 302. Organization: anthropic. License: Proprietary.

94.9% percentile inside its fair comparison set

1,469Raw benchmark valueCI 1,435 - 1,503

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_software_and_it_services. Source rank: #3. Votes: 1587. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,502 - 1,532

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1146. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,487 - 1,524

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #5 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.9%
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Anthropic.

91.1% percentile inside its fair comparison set

51.9%Raw benchmark valueCI 45.2% - 58.6%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.7%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench-v1; provider: Anthropic.

100% percentile inside its fair comparison set

71.7%Raw benchmark valueCI 69.4% - 73.9%

Search / tool use3 benchmarks97.6%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #6 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 98.5%
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

99.4% percentile inside its fair comparison set

98.5%Raw benchmark value

Search Arena

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 5007. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,228 - 1,249

Search Arena · No Style Control

AR · Search / tool use · Human

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,237
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #3. Votes: 5007. Organization: anthropic. License: Proprietary.

93.3% percentile inside its fair comparison set

1,237Raw benchmark valueCI 1,227 - 1,248

Long context2 benchmarks99.4%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #5 · Source label: Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 70%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

98.7% percentile inside its fair comparison set

70%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Anthropic.

100% percentile inside its fair comparison set

71.8%Raw benchmark valueCI 70.1% - 73.6%

Vision understanding11 benchmarks99.5%

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,307
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #2. Votes: 1785. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,307Raw benchmark valueCI 1,292 - 1,323

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: diagram. Source rank: #1. Votes: 497. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,315 - 1,371

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #3. Votes: 840. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,281 - 1,324

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,335
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: homework. Source rank: #2. Votes: 286. Organization: anthropic. License: Proprietary.

98.5% percentile inside its fair comparison set

1,335Raw benchmark valueCI 1,299 - 1,371

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: ocr. Source rank: #1. Votes: 1342. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,306 - 1,340

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 1785. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,308 - 1,338

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: diagram. Source rank: #1. Votes: 497. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,319 - 1,375

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: english. Source rank: #4. Votes: 840. Organization: anthropic. License: Proprietary.

98.2% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,300 - 1,343

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,345
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: homework. Source rank: #1. Votes: 286. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,345Raw benchmark valueCI 1,308 - 1,381

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: ocr. Source rank: #1. Votes: 1342. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,317 - 1,351

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Anthropic.

100% percentile inside its fair comparison set

89.3%Raw benchmark valueCI 87.8% - 90.8%

Document understanding4 benchmarks96.2%

Document Arena

AR · Document understanding · Human

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #1. Votes: 1461. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,485 - 1,515

Document Arena · No Style Control

AR · Document understanding · Human

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: overall. Source rank: #5. Votes: 1461. Organization: anthropic. License: Proprietary.

91.7% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,480 - 1,510

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #1 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: Anthropic.

100% percentile inside its fair comparison set

74Raw benchmark valueCI 73 - 75

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #5 · Source label: anthropic/claude-fable-5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.9%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Anthropic.

93.3% percentile inside its fair comparison set

68.9%Raw benchmark valueCI 67.1% - 70.7%

Multilingual4 benchmarks99.5%

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: french. Source rank: #3. Votes: 193. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,478 - 1,570

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: russian. Source rank: #1. Votes: 382. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,502 - 1,564

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: french. Source rank: #3. Votes: 193. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,458 - 1,549

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-fable-5`. Category: russian. Source rank: #1. Votes: 382. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,488 - 1,550