Model profile · Anthropic

Claude Opus 4.7

Closed weightsfrontier · registry tag 2026 flagship

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 39%
Verified coverage: 36.3%
Spread: 93.5%
Last verified: Jun 20, 2026

80%bench fit

textcodevisiondocumentsearch7 aliases44 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 / text28 benchmarks79.5%

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 #8 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.2% percentile inside its fair comparison set

43Raw 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 #11 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.5%
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

96.6% percentile inside its fair comparison set

43.5%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 #38 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.1%
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

87.6% percentile inside its fair comparison set

48.1%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 #135 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.6%
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

57.5% percentile inside its fair comparison set

43.6%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 #260 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M tokens
Percentile: 6.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

6.5% percentile inside its fair comparison set

$10 /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 #262 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M input tokens
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

6.9% percentile inside its fair comparison set

$5 /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 #260 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $25 /1M output tokens
Percentile: 6.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

6.5% percentile inside its fair comparison set

$25 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #176 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.5 tokens/s
Percentile: 16.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

16.7% percentile inside its fair comparison set

48.5 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #183 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.81s
Percentile: 13.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

13.3% percentile inside its fair comparison set

13.81sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #109 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.81s
Percentile: 48.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

48.6% percentile inside its fair comparison set

13.81sRaw 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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #3. Votes: 32629. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,498 - 1,507

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing. Source rank: #3. Votes: 5500. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,477 - 1,495

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #3. Votes: 15799. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,503 - 1,514

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: exclude_ties. Source rank: #3. Votes: 25085. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,514 - 1,526

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts. Source rank: #4. Votes: 21557. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,519 - 1,530

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts_english. Source rank: #4. Votes: 10929. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,520 - 1,534

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: instruction_following. Source rank: #3. Votes: 11075. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,497 - 1,511

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,514
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: longer_query. Source rank: #4. Votes: 14253. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,514Raw benchmark valueCI 1,508 - 1,521

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 #2 · Source label: claude-opus-4-7-thinking

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-opus-4-7-thinking`. Category: multi_turn. Source rank: #2. Votes: 5605. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,508 - 1,526

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #4. Votes: 32629. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,485 - 1,494

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 #5 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing. Source rank: #6. Votes: 5500. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,472 - 1,490

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #4. Votes: 15799. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,488 - 1,499

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: exclude_ties. Source rank: #4. Votes: 25085. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,494 - 1,506

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts. Source rank: #4. Votes: 21557. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,497 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts_english. Source rank: #4. Votes: 10929. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,498 - 1,512

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: instruction_following. Source rank: #4. Votes: 11075. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,504

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: longer_query. Source rank: #4. Votes: 14253. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,496 - 1,509

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 #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: multi_turn. Source rank: #3. Votes: 5978. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,496 - 1,514

Coding22 benchmarks90.1%

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 #4 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.5%
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

99% percentile inside its fair comparison set

51.5%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 #8 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 50.1%
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

98.1% percentile inside its fair comparison set

50.1%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 #3 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

97.3% percentile inside its fair comparison set

74Raw 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 #3 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

95.7% percentile inside its fair comparison set

44Raw 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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #4. Votes: 7823. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,555 - 1,571

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: webdev. Source rank: #4. Votes: 7823. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,555 - 1,571

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 #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,559
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: webdev-html. Source rank: #2. Votes: 905. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,559Raw benchmark valueCI 1,538 - 1,580

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,560
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: webdev-react. Source rank: #3. Votes: 6797. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,560Raw benchmark valueCI 1,552 - 1,569

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.9%
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

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

86.4% percentile inside its fair comparison set

43.9%Raw benchmark valueCI 35.6% - 52.1%

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 #19 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.1%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

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

80% percentile inside its fair comparison set

85.1%Raw benchmark valueCI 83.1% - 87%

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 #7 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

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

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

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 #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82%
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

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

92.6% percentile inside its fair comparison set

82%Raw benchmark valueCI 78.6% - 85.4%

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 #6 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.5%
Percentile: 81.5%
Last updated: recent
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

68.5%Raw benchmark valueCI 66% - 71.1%

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 #3 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71%
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

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

95.9% percentile inside its fair comparison set

71%Raw benchmark valueCI 62.2% - 79.8%

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,553
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: coding. Source rank: #2. Votes: 9252. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,553Raw benchmark valueCI 1,546 - 1,561

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: coding. Source rank: #4. Votes: 9252. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,512 - 1,527

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.1%
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

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

93.2% percentile inside its fair comparison set

47.1%Raw benchmark valueCI 30% - 64.1%

Code Arena · Image To Webdev

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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,581
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: image_to_webdev. Source rank: #1. Votes: 2075. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,581Raw benchmark valueCI 1,566 - 1,596

HiL-Bench

SL · Coding · Rubric

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 27.7%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Manually verified from the official Scale Labs HiL-Bench leaderboard.

80% percentile inside its fair comparison set

27.7%Raw benchmark value

Terminal-Bench 2.0

OFF · Coding · Objective

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

Rank #3

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 69.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

66.7% percentile inside its fair comparison set

69.4%Raw benchmark value

SWE-Bench Verified

OFF · Coding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 87.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published SWE-Bench Verified figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

87.6%Raw benchmark value

Terminal-Bench 2.0

TERMINAL-BENCH · Coding · Objective

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

Rank #15 · Source label: claude-opus-4-1-20250805

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 38%
Percentile: 60%
Last updated: archived
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from the public Terminal-Bench 2.0 verified leaderboard. Collapse policy: highest verified score per canonical model. Selected agent: Terminus 2 (2.0.0). Display model: Claude Opus 4.1. Integration method: API. Agent URL: https://www.tbench.ai/terminus. Reported stderr: 1.339 percentage points. Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

60% percentile inside its fair comparison set

38%Raw benchmark value

Reasoning / math / science10 benchmarks91.7%

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 #12 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.2%
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

97% percentile inside its fair comparison set

31.2%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 #13 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 88.5%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

96.8% percentile inside its fair comparison set

88.5%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 #16 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.1%
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

95.4% percentile inside its fair comparison set

5.1%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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54%
Percentile: 91.4%
Last updated: recent
Eligibility: headline eligible

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

91.4% percentile inside its fair comparison set

54%Raw benchmark valueCI 44.2% - 63.8%

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 #12 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.2%
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

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

88.8% percentile inside its fair comparison set

90.2%Raw benchmark valueCI 87.1% - 93.2%

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.9%
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

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

96.6% percentile inside its fair comparison set

89.9%Raw benchmark valueCI 89.3% - 90.5%

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: math. Source rank: #5. Votes: 1779. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,490 - 1,518

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: math. Source rank: #5. Votes: 1779. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,483 - 1,512

Humanity's Last Exam

OFF · Reasoning / math / science · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 46.9%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published no-tools Humanity's Last Exam figure. Checked 2026-04-29. Verification: manual_public_page_verification.

100% percentile inside its fair comparison set

46.9%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #11 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 62%
Percentile: 53.3%
Last updated: aging
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

53.3% percentile inside its fair comparison set

62%Raw benchmark value

Professional reasoning26 benchmarks96%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #4 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,507
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

1,507Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

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

88.5% percentile inside its fair comparison set

66Raw benchmark valueCI 64 - 69

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #11 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.3%
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

85.3%Raw benchmark valueCI 84.4% - 86.1%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.5%
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

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

84% percentile inside its fair comparison set

51.5%Raw benchmark valueCI 50.5% - 52.5%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #10 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.3%
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

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

90.1% percentile inside its fair comparison set

75.3%Raw benchmark valueCI 73.6% - 76.9%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.9%
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

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

92.2% percentile inside its fair comparison set

54.9%Raw benchmark valueCI 50.5% - 59.2%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #16 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83%
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

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

70% percentile inside its fair comparison set

83%Raw benchmark valueCI 79.1% - 86.8%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: expert. Source rank: #4. Votes: 3228. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,521 - 1,544

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #5. Votes: 6482. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,492 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #3. Votes: 7042. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,489

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_legal_and_government. Source rank: #5. Votes: 2601. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,492 - 1,518

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #1. Votes: 5573. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,518 - 1,536

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_mathematical. Source rank: #4. Votes: 1889. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,500 - 1,530

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 2450. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,508 - 1,534

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,543
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_software_and_it_services. Source rank: #2. Votes: 13041. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,543Raw benchmark valueCI 1,536 - 1,549

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #3. Votes: 7935. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,487 - 1,502

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: expert. Source rank: #4. Votes: 3228. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,505 - 1,528

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #3. Votes: 6482. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,473 - 1,490

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #4. Votes: 7042. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,464 - 1,480

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_legal_and_government. Source rank: #4. Votes: 2601. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,484 - 1,509

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #3. Votes: 5573. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,499 - 1,516

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_mathematical. Source rank: #5. Votes: 1889. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,492 - 1,521

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_medicine_and_healthcare. Source rank: #4. Votes: 2450. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,483 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_software_and_it_services. Source rank: #4. Votes: 13041. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,510 - 1,523

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #4. Votes: 7935. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,480 - 1,496

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #1 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

56.1%Raw benchmark valueCI 49.5% - 62.7%

Search / tool use4 benchmarks71.5%

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 #85 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74%
Percentile: 72.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

72.8% percentile inside its fair comparison set

74%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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: overall. Source rank: #4. Votes: 38472. Organization: anthropic. License: Proprietary.

90% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,205 - 1,216

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: overall. Source rank: #4. Votes: 38472. Organization: anthropic. License: Proprietary.

90% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,227 - 1,238

BrowseComp

OFF · Search / tool use · Objective

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

Rank #5

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 79.3%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published BrowseComp figure. Checked 2026-04-29. Verification: manual_public_page_verification.

33.3% percentile inside its fair comparison set

79.3%Raw benchmark value

Long context2 benchmarks90.1%

Long Context Reasoning

AA · Long context · Objective

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

Rank #17 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67%
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

94.9% percentile inside its fair comparison set

67%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 #14 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.1%
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

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

85.2% percentile inside its fair comparison set

66.1%Raw benchmark valueCI 64.3% - 67.9%

Vision understanding17 benchmarks94.8%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #10 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.4%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

93.3% percentile inside its fair comparison set

76.4%Raw benchmark value

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,309
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #1. Votes: 13312. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,309Raw benchmark valueCI 1,301 - 1,316

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing_vision. Source rank: #3. Votes: 762. Organization: anthropic. License: Proprietary.

96.4% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,292 - 1,337

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: diagram. Source rank: #2. Votes: 3646. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,331 - 1,354

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #1. Votes: 5936. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,300 - 1,321

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 #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: homework. Source rank: #3. Votes: 2217. Organization: anthropic. License: Proprietary.

97.1% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,316 - 1,344

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: humor. Source rank: #3. Votes: 506. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,280 - 1,335

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: ocr. Source rank: #2. Votes: 9614. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,315 - 1,331

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #2. Votes: 13312. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,315 - 1,330

Vision Arena · Creative Writing Vision · 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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,335
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing_vision. Source rank: #3. Votes: 762. Organization: anthropic. License: Proprietary.

96.4% percentile inside its fair comparison set

1,335Raw benchmark valueCI 1,312 - 1,357

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,344
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: diagram. Source rank: #2. Votes: 3646. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,344Raw benchmark valueCI 1,333 - 1,356

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,327
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #1. Votes: 5936. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,327Raw benchmark valueCI 1,317 - 1,338

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 #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: homework. Source rank: #2. Votes: 2217. Organization: anthropic. License: Proprietary.

98.5% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,324 - 1,352

Vision Arena · Humor · 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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: humor. Source rank: #3. Votes: 506. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,298 - 1,353

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,332
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: ocr. Source rank: #2. Votes: 9614. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,332Raw benchmark valueCI 1,324 - 1,340

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 #12 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.5%
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

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

81% percentile inside its fair comparison set

85.5%Raw benchmark valueCI 83.9% - 87.2%

VISTA

SL · Vision understanding · Rubric

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

Rank #9 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 77%
Percentile: 64.3%
Last updated: aging
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

64.3% percentile inside its fair comparison set

77%Raw benchmark value

Document understanding5 benchmarks88%

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #2. Votes: 13878. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,504

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #3. Votes: 13878. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

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

84.2% percentile inside its fair comparison set

67Raw benchmark valueCI 65 - 70

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 #1 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

70.3%Raw benchmark valueCI 68.5% - 72%

Multimodal mix

OC · Document understanding · Objective

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

Rank #9 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: OpenCompass
Raw value: 74.2%
Percentile: 64.3%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

64.3% percentile inside its fair comparison set

74.2%Raw benchmark value

Multilingual16 benchmarks98.5%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #3. Votes: 1738. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,529 - 1,560

Text Arena · French

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: french. Source rank: #4. Votes: 1116. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,497 - 1,538

Text Arena · German

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: german. Source rank: #3. Votes: 443. Organization: anthropic. License: Proprietary.

99.2% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,481 - 1,537

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: japanese. Source rank: #5. Votes: 338. Organization: anthropic. License: Proprietary.

98% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,460 - 1,532

Text Arena · Korean

AR · Multilingual · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: korean. Source rank: #3. Votes: 523. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,439 - 1,493

Text Arena · Russian

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: russian. Source rank: #4. Votes: 3359. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,495 - 1,517

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: spanish. Source rank: #3. Votes: 1045. Organization: anthropic. License: Proprietary.

99.5% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,464 - 1,504

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #5. Votes: 1738. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,521 - 1,551

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: french. Source rank: #5. Votes: 1116. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,483 - 1,523

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: german. Source rank: #3. Votes: 443. Organization: anthropic. License: Proprietary.

99.2% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,471 - 1,528

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: japanese. Source rank: #7. Votes: 338. Organization: anthropic. License: Proprietary.

97% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,446 - 1,517

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #6

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: korean. Source rank: #6. Votes: 523. Organization: anthropic. License: Proprietary.

97.6% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,430 - 1,484

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: russian. Source rank: #7. Votes: 3359. Organization: anthropic. License: Proprietary.

98.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,483 - 1,505

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: spanish. Source rank: #4. Votes: 1045. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,458 - 1,497

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #3. Votes: 713. Organization: anthropic. License: Proprietary.

97.4% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,322 - 1,376

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #4. Votes: 713. Organization: anthropic. License: Proprietary.

96.1% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,341 - 1,394

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

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 Opus 4.7

Closed weightsfrontier · registry tag 2026 flagship

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 39%
Verified coverage: 36.3%
Spread: 93.5%
Last verified: Jun 20, 2026

80%bench fit

textcodevisiondocumentsearch7 aliases44 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 / text28 benchmarks79.5%

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 #8 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.2% percentile inside its fair comparison set

43Raw 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 #11 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.5%
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

96.6% percentile inside its fair comparison set

43.5%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 #38 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.1%
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

87.6% percentile inside its fair comparison set

48.1%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 #135 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.6%
Percentile: 57.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

57.5% percentile inside its fair comparison set

43.6%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 #260 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M tokens
Percentile: 6.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

6.5% percentile inside its fair comparison set

$10 /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 #262 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M input tokens
Percentile: 6.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

6.9% percentile inside its fair comparison set

$5 /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 #260 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $25 /1M output tokens
Percentile: 6.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

6.5% percentile inside its fair comparison set

$25 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

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

Rank #176 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 48.5 tokens/s
Percentile: 16.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

16.7% percentile inside its fair comparison set

48.5 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

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

Rank #183 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.81s
Percentile: 13.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

13.3% percentile inside its fair comparison set

13.81sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

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

Rank #109 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.81s
Percentile: 48.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

48.6% percentile inside its fair comparison set

13.81sRaw 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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #3. Votes: 32629. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,498 - 1,507

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing. Source rank: #3. Votes: 5500. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,477 - 1,495

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #3. Votes: 15799. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,503 - 1,514

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: exclude_ties. Source rank: #3. Votes: 25085. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,514 - 1,526

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts. Source rank: #4. Votes: 21557. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,519 - 1,530

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts_english. Source rank: #4. Votes: 10929. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,520 - 1,534

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: instruction_following. Source rank: #3. Votes: 11075. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,497 - 1,511

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,514
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: longer_query. Source rank: #4. Votes: 14253. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,514Raw benchmark valueCI 1,508 - 1,521

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 #2 · Source label: claude-opus-4-7-thinking

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-opus-4-7-thinking`. Category: multi_turn. Source rank: #2. Votes: 5605. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,508 - 1,526

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #4. Votes: 32629. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,485 - 1,494

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 #5 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing. Source rank: #6. Votes: 5500. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,472 - 1,490

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #4. Votes: 15799. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,488 - 1,499

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: exclude_ties. Source rank: #4. Votes: 25085. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,494 - 1,506

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts. Source rank: #4. Votes: 21557. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,497 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: hard_prompts_english. Source rank: #4. Votes: 10929. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,498 - 1,512

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: instruction_following. Source rank: #4. Votes: 11075. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,504

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: longer_query. Source rank: #4. Votes: 14253. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,496 - 1,509

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 #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: multi_turn. Source rank: #3. Votes: 5978. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,496 - 1,514

Coding22 benchmarks90.1%

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 #4 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.5%
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

99% percentile inside its fair comparison set

51.5%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 #8 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 50.1%
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

98.1% percentile inside its fair comparison set

50.1%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 #3 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

97.3% percentile inside its fair comparison set

74Raw 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 #3 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

95.7% percentile inside its fair comparison set

44Raw 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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #4. Votes: 7823. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,555 - 1,571

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: webdev. Source rank: #4. Votes: 7823. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,555 - 1,571

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 #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,559
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: webdev-html. Source rank: #2. Votes: 905. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,559Raw benchmark valueCI 1,538 - 1,580

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,560
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: webdev-react. Source rank: #3. Votes: 6797. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,560Raw benchmark valueCI 1,552 - 1,569

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.9%
Percentile: 86.4%
Last updated: recent
Eligibility: headline eligible

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

86.4% percentile inside its fair comparison set

43.9%Raw benchmark valueCI 35.6% - 52.1%

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 #19 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.1%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

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

80% percentile inside its fair comparison set

85.1%Raw benchmark valueCI 83.1% - 87%

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 #7 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

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

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

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 #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82%
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

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

92.6% percentile inside its fair comparison set

82%Raw benchmark valueCI 78.6% - 85.4%

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 #6 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.5%
Percentile: 81.5%
Last updated: recent
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

68.5%Raw benchmark valueCI 66% - 71.1%

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 #3 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71%
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

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

95.9% percentile inside its fair comparison set

71%Raw benchmark valueCI 62.2% - 79.8%

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,553
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: coding. Source rank: #2. Votes: 9252. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,553Raw benchmark valueCI 1,546 - 1,561

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,520
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: coding. Source rank: #4. Votes: 9252. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,520Raw benchmark valueCI 1,512 - 1,527

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.1%
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

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

93.2% percentile inside its fair comparison set

47.1%Raw benchmark valueCI 30% - 64.1%

Code Arena · Image To Webdev

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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,581
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: image_to_webdev. Source rank: #1. Votes: 2075. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,581Raw benchmark valueCI 1,566 - 1,596

HiL-Bench

SL · Coding · Rubric

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

Rank #2

verified runtimeexact direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 27.7%
Percentile: 80%
Last updated: recent
Eligibility: headline eligible

Manually verified from the official Scale Labs HiL-Bench leaderboard.

80% percentile inside its fair comparison set

27.7%Raw benchmark value

Terminal-Bench 2.0

OFF · Coding · Objective

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

Rank #3

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 69.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

66.7% percentile inside its fair comparison set

69.4%Raw benchmark value

SWE-Bench Verified

OFF · Coding · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 87.6%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

87.6%Raw benchmark value

Terminal-Bench 2.0

TERMINAL-BENCH · Coding · Objective

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

Rank #15 · Source label: claude-opus-4-1-20250805

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 38%
Percentile: 60%
Last updated: archived
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

60% percentile inside its fair comparison set

38%Raw benchmark value

Reasoning / math / science10 benchmarks91.7%

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 #12 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.2%
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

97% percentile inside its fair comparison set

31.2%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 #13 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 88.5%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

96.8% percentile inside its fair comparison set

88.5%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 #16 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.1%
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

95.4% percentile inside its fair comparison set

5.1%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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54%
Percentile: 91.4%
Last updated: recent
Eligibility: headline eligible

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

91.4% percentile inside its fair comparison set

54%Raw benchmark valueCI 44.2% - 63.8%

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 #12 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.2%
Percentile: 88.8%
Last updated: recent
Eligibility: headline eligible

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

88.8% percentile inside its fair comparison set

90.2%Raw benchmark valueCI 87.1% - 93.2%

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.9%
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

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

96.6% percentile inside its fair comparison set

89.9%Raw benchmark valueCI 89.3% - 90.5%

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: math. Source rank: #5. Votes: 1779. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,490 - 1,518

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: math. Source rank: #5. Votes: 1779. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,483 - 1,512

Humanity's Last Exam

OFF · Reasoning / math / science · Objective

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

Rank #1

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 46.9%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

46.9%Raw benchmark value

EnigmaEval

SL · Reasoning / math / science · Rubric

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

Rank #11 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 62%
Percentile: 53.3%
Last updated: aging
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

53.3% percentile inside its fair comparison set

62%Raw benchmark value

Professional reasoning26 benchmarks96%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #4 · Source label: Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,507
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

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

93.5% percentile inside its fair comparison set

1,507Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66
Percentile: 88.5%
Last updated: recent
Eligibility: headline eligible

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

88.5% percentile inside its fair comparison set

66Raw benchmark valueCI 64 - 69

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #11 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.3%
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

85.3%Raw benchmark valueCI 84.4% - 86.1%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.5%
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

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

84% percentile inside its fair comparison set

51.5%Raw benchmark valueCI 50.5% - 52.5%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #10 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.3%
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

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

90.1% percentile inside its fair comparison set

75.3%Raw benchmark valueCI 73.6% - 76.9%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #5 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.9%
Percentile: 92.2%
Last updated: recent
Eligibility: headline eligible

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

92.2% percentile inside its fair comparison set

54.9%Raw benchmark valueCI 50.5% - 59.2%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #16 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83%
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

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

70% percentile inside its fair comparison set

83%Raw benchmark valueCI 79.1% - 86.8%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: expert. Source rank: #4. Votes: 3228. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,521 - 1,544

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 #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

99.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,492 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

99.4% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,472 - 1,489

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_legal_and_government. Source rank: #5. Votes: 2601. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,492 - 1,518

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,518 - 1,536

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,515
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_mathematical. Source rank: #4. Votes: 1889. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,515Raw benchmark valueCI 1,500 - 1,530

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 2450. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,508 - 1,534

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,543
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_software_and_it_services. Source rank: #2. Votes: 13041. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,543Raw benchmark valueCI 1,536 - 1,549

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

99.4% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,487 - 1,502

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: expert. Source rank: #4. Votes: 3228. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,505 - 1,528

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

99.7% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,473 - 1,490

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

99.4% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,464 - 1,480

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_legal_and_government. Source rank: #4. Votes: 2601. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,484 - 1,509

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

99.7% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,499 - 1,516

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_mathematical. Source rank: #5. Votes: 1889. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,492 - 1,521

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_medicine_and_healthcare. Source rank: #4. Votes: 2450. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,483 - 1,508

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: industry_software_and_it_services. Source rank: #4. Votes: 13041. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,510 - 1,523

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 #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

99.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,480 - 1,496

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #1 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

56.1%Raw benchmark valueCI 49.5% - 62.7%

Search / tool use4 benchmarks71.5%

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 #85 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74%
Percentile: 72.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

72.8% percentile inside its fair comparison set

74%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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,211
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: overall. Source rank: #4. Votes: 38472. Organization: anthropic. License: Proprietary.

90% percentile inside its fair comparison set

1,211Raw benchmark valueCI 1,205 - 1,216

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,232
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: overall. Source rank: #4. Votes: 38472. Organization: anthropic. License: Proprietary.

90% percentile inside its fair comparison set

1,232Raw benchmark valueCI 1,227 - 1,238

BrowseComp

OFF · Search / tool use · Objective

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

Rank #5

Official company resultmanual verifiedmanual verified

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Provider official evals
Raw value: 79.3%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published BrowseComp figure. Checked 2026-04-29. Verification: manual_public_page_verification.

33.3% percentile inside its fair comparison set

79.3%Raw benchmark value

Long context2 benchmarks90.1%

Long Context Reasoning

AA · Long context · Objective

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

Rank #17 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67%
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

94.9% percentile inside its fair comparison set

67%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 #14 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.1%
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

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

85.2% percentile inside its fair comparison set

66.1%Raw benchmark valueCI 64.3% - 67.9%

Vision understanding17 benchmarks94.8%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #10 · Source label: Claude Opus 4.7 (Non-reasoning, High Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 76.4%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

93.3% percentile inside its fair comparison set

76.4%Raw benchmark value

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,309
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #1. Votes: 13312. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,309Raw benchmark valueCI 1,301 - 1,316

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing_vision. Source rank: #3. Votes: 762. Organization: anthropic. License: Proprietary.

96.4% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,292 - 1,337

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: diagram. Source rank: #2. Votes: 3646. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,331 - 1,354

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #1. Votes: 5936. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,300 - 1,321

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 #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: homework. Source rank: #3. Votes: 2217. Organization: anthropic. License: Proprietary.

97.1% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,316 - 1,344

Vision Arena · Humor

AR · Vision understanding · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: humor. Source rank: #3. Votes: 506. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,280 - 1,335

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: ocr. Source rank: #2. Votes: 9614. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,315 - 1,331

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #2. Votes: 13312. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,315 - 1,330

Vision Arena · Creative Writing Vision · 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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,335
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: creative_writing_vision. Source rank: #3. Votes: 762. Organization: anthropic. License: Proprietary.

96.4% percentile inside its fair comparison set

1,335Raw benchmark valueCI 1,312 - 1,357

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,344
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: diagram. Source rank: #2. Votes: 3646. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,344Raw benchmark valueCI 1,333 - 1,356

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 #1 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,327
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: english. Source rank: #1. Votes: 5936. Organization: anthropic. License: Proprietary.

100% percentile inside its fair comparison set

1,327Raw benchmark valueCI 1,317 - 1,338

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 #2

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: homework. Source rank: #2. Votes: 2217. Organization: anthropic. License: Proprietary.

98.5% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,324 - 1,352

Vision Arena · Humor · 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 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 95.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: humor. Source rank: #3. Votes: 506. Organization: anthropic. License: Proprietary.

95.9% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,298 - 1,353

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,332
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: ocr. Source rank: #2. Votes: 9614. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,332Raw benchmark valueCI 1,324 - 1,340

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 #12 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.5%
Percentile: 81%
Last updated: recent
Eligibility: headline eligible

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

81% percentile inside its fair comparison set

85.5%Raw benchmark valueCI 83.9% - 87.2%

VISTA

SL · Vision understanding · Rubric

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

Rank #9 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 77%
Percentile: 64.3%
Last updated: aging
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

64.3% percentile inside its fair comparison set

77%Raw benchmark value

Document understanding5 benchmarks88%

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #2. Votes: 13878. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,490 - 1,504

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 #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: overall. Source rank: #3. Votes: 13878. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

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 #4 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

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

84.2% percentile inside its fair comparison set

67Raw benchmark valueCI 65 - 70

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 #1 · Source label: anthropic/claude-opus-4-7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.3%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

70.3%Raw benchmark valueCI 68.5% - 72%

Multimodal mix

OC · Document understanding · Objective

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

Rank #9 · Source label: claude-opus-4-1

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: OpenCompass
Raw value: 74.2%
Percentile: 64.3%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Backfilled from Claude Opus 4.1 via approved benchmark identity mapping map-claude-opus-4-7-to-4-1.

64.3% percentile inside its fair comparison set

74.2%Raw benchmark value

Multilingual16 benchmarks98.5%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #3. Votes: 1738. Organization: anthropic. License: Proprietary.

99.7% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,529 - 1,560

Text Arena · French

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: french. Source rank: #4. Votes: 1116. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,497 - 1,538

Text Arena · German

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: german. Source rank: #3. Votes: 443. Organization: anthropic. License: Proprietary.

99.2% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,481 - 1,537

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: japanese. Source rank: #5. Votes: 338. Organization: anthropic. License: Proprietary.

98% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,460 - 1,532

Text Arena · Korean

AR · Multilingual · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: korean. Source rank: #3. Votes: 523. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,439 - 1,493

Text Arena · Russian

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: russian. Source rank: #4. Votes: 3359. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,495 - 1,517

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #2 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: spanish. Source rank: #3. Votes: 1045. Organization: anthropic. License: Proprietary.

99.5% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,464 - 1,504

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #5. Votes: 1738. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,521 - 1,551

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: french. Source rank: #5. Votes: 1116. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,483 - 1,523

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: german. Source rank: #3. Votes: 443. Organization: anthropic. License: Proprietary.

99.2% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,471 - 1,528

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: japanese. Source rank: #7. Votes: 338. Organization: anthropic. License: Proprietary.

97% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,446 - 1,517

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #6

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7`. Category: korean. Source rank: #6. Votes: 523. Organization: anthropic. License: Proprietary.

97.6% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,430 - 1,484

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: russian. Source rank: #7. Votes: 3359. Organization: anthropic. License: Proprietary.

98.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,483 - 1,505

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: spanish. Source rank: #4. Votes: 1045. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,458 - 1,497

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #3 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #3. Votes: 713. Organization: anthropic. License: Proprietary.

97.4% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,322 - 1,376

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #4 · Source label: claude-opus-4-7-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-7-thinking`. Category: chinese. Source rank: #4. Votes: 713. Organization: anthropic. License: Proprietary.

96.1% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,341 - 1,394