Model profile · Anthropic

Claude Opus 4.8

Closed weightsfrontier · registry tag 2026 current

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 34.9%
Verified coverage: 34.9%
Spread: 94.3%
Last verified: Jun 20, 2026

84%bench fit

textcodevisiondocument4 aliases39 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 benchmarks78.8%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

99.7% percentile inside its fair comparison set

56Raw 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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.6%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

98.7% percentile inside its fair comparison set

46.6%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 #21 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.1%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

93.3% percentile inside its fair comparison set

64.1%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 #53 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.2%
Percentile: 83.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

83.5% percentile inside its fair comparison set

62.2%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 #261 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #263 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #261 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #132 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.8 tokens/s
Percentile: 37.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

37.6% percentile inside its fair comparison set

69.8 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 #199 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.32s
Percentile: 5.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

5.7% percentile inside its fair comparison set

33.32sRaw 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 #164 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.32s
Percentile: 22.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

22.4% percentile inside its fair comparison set

33.32sRaw 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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #12. Votes: 13316. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,472 - 1,484

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 #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing. Source rank: #16. Votes: 2317. Organization: anthropic. License: Proprietary.

96.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,444 - 1,470

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #11. Votes: 6464. Organization: anthropic. License: Proprietary.

97.5% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,493

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: exclude_ties. Source rank: #11. Votes: 9999. Organization: anthropic. License: Proprietary.

97.5% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,497

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts. Source rank: #7. Votes: 8692. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,520

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts_english. Source rank: #6. Votes: 4444. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,506 - 1,526

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: instruction_following. Source rank: #7. Votes: 4330. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,476 - 1,495

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: longer_query. Source rank: #6. Votes: 5865. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,499 - 1,517

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: multi_turn. Source rank: #7. Votes: 2421. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,487 - 1,512

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #23. Votes: 13316. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,448 - 1,461

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 #21

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing. Source rank: #26. Votes: 2317. Organization: anthropic. License: Proprietary.

93.8% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,424 - 1,450

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #23. Votes: 6464. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,453 - 1,469

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: exclude_ties. Source rank: #23. Votes: 9999. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,447 - 1,463

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 #16

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts. Source rank: #20. Votes: 8692. Organization: anthropic. License: Proprietary.

95.4% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,486

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts_english. Source rank: #10. Votes: 4444. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,474 - 1,493

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 #12

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: instruction_following. Source rank: #16. Votes: 4330. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,477

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: longer_query. Source rank: #6. Votes: 5865. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: multi_turn. Source rank: #14. Votes: 2421. Organization: anthropic. License: Proprietary.

96.9% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,464 - 1,489

Coding16 benchmarks96.2%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.3%
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

99.7% percentile inside its fair comparison set

58.3%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 #3 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.5%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

99.5% percentile inside its fair comparison set

53.5%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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

98.7% 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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

97.8% percentile inside its fair comparison set

47Raw 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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #6. Votes: 3441. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,531 - 1,553

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev. Source rank: #6. Votes: 3441. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,531 - 1,553

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 #6

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,529
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev-html. Source rank: #8. Votes: 484. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,529Raw benchmark valueCI 1,501 - 1,557

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,541
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev-react. Source rank: #6. Votes: 2950. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,541Raw benchmark valueCI 1,529 - 1,552

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.3%
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

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

95.5% percentile inside its fair comparison set

47.3%Raw benchmark valueCI 39.1% - 55.4%

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 #4 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.8%
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

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

96.7% percentile inside its fair comparison set

87.8%Raw benchmark valueCI 86% - 89.7%

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1%
Percentile: 95%
Last updated: recent
Eligibility: headline eligible

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

95% percentile inside its fair comparison set

1%Raw benchmark valueCI 0% - 2.4%

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.6%
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

88.6%Raw benchmark valueCI 85.8% - 91.4%

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 #4 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.9%
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

71.9%Raw benchmark valueCI 70.6% - 73.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.7%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

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

98% percentile inside its fair comparison set

82.7%Raw benchmark valueCI 76.7% - 88.8%

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,540
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: coding. Source rank: #7. Votes: 3592. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,540Raw benchmark valueCI 1,529 - 1,550

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: coding. Source rank: #14. Votes: 3592. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,486 - 1,507

Reasoning / math / science8 benchmarks97.5%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.7%
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

99.7% percentile inside its fair comparison set

45.7%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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 92%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

98.9% percentile inside its fair comparison set

92%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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.9%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

98.7% percentile inside its fair comparison set

20.9%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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69%
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

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

97.1% percentile inside its fair comparison set

69%Raw benchmark valueCI 59.9% - 78.1%

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 #6 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 92.4%
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

92.4%Raw benchmark valueCI 88.5% - 96.3%

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 #5 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

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

95.5% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 89% - 90.2%

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 #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: math. Source rank: #9. Votes: 648. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,473 - 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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: math. Source rank: #11. Votes: 648. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,465 - 1,510

Professional reasoning31 benchmarks94.6%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,605
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

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

97.8% percentile inside its fair comparison set

1,605Raw benchmark value

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #1 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

43.8%Raw benchmark valueCI 37% - 50.5%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.2%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

59.2%Raw benchmark valueCI 50.4% - 68%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #1 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

68.1%Raw benchmark valueCI 65.8% - 70.5%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

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

96.2% percentile inside its fair comparison set

70Raw benchmark valueCI 69 - 72

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 9.6%
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

9.6%Raw benchmark valueCI 5.4% - 13.8%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #30 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.6%
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

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

67.8% percentile inside its fair comparison set

83.6%Raw benchmark valueCI 82.6% - 84.5%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #3 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.9%
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

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

92% percentile inside its fair comparison set

53.9%Raw benchmark valueCI 53.6% - 54.2%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #8 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.6%
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

75.6%Raw benchmark valueCI 74% - 77.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #6 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.2%
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

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

90.2% percentile inside its fair comparison set

53.2%Raw benchmark valueCI 49% - 57.5%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #7 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.8%
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

85.8%Raw benchmark valueCI 82% - 89.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: expert. Source rank: #5. Votes: 1258. Organization: anthropic. License: Proprietary.

98.9% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,513 - 1,547

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 #3

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-4-8`. Category: industry_business_and_management_and_financial_operations. Source rank: #4. Votes: 2601. Organization: anthropic. License: Proprietary.

99.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,488 - 1,512

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 2946. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,446 - 1,469

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_legal_and_government. Source rank: #3. Votes: 1020. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,490 - 1,530

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_life_and_physical_and_social_science. Source rank: #12. Votes: 2213. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,484 - 1,510

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_mathematical. Source rank: #9. Votes: 668. Organization: anthropic. License: Proprietary.

97.7% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,479 - 1,525

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_medicine_and_healthcare. Source rank: #13. Votes: 982. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,479 - 1,518

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_software_and_it_services. Source rank: #7. Votes: 5156. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,515 - 1,533

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_writing_and_literature_and_language. Source rank: #13. Votes: 3391. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,456 - 1,477

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: expert. Source rank: #11. Votes: 1258. Organization: anthropic. License: Proprietary.

97.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,486 - 1,520

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_business_and_management_and_financial_operations. Source rank: #12. Votes: 2601. Organization: anthropic. License: Proprietary.

97.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,450 - 1,475

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 #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_entertainment_and_sports_and_media. Source rank: #22. Votes: 2946. Organization: anthropic. License: Proprietary.

94.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,445

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_legal_and_government. Source rank: #10. Votes: 1020. Organization: anthropic. License: Proprietary.

97.3% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,463 - 1,502

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 #23

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_life_and_physical_and_social_science. Source rank: #28. Votes: 2213. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,452 - 1,478

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_mathematical. Source rank: #11. Votes: 668. Organization: anthropic. License: Proprietary.

97.4% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,469 - 1,515

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 #37

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_medicine_and_healthcare. Source rank: #40. Votes: 982. Organization: anthropic. License: Proprietary.

87.8% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,436 - 1,474

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 #14

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_software_and_it_services. Source rank: #17. Votes: 5156. Organization: anthropic. License: Proprietary.

96% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #17

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 95.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_writing_and_literature_and_language. Source rank: #21. Votes: 3391. Organization: anthropic. License: Proprietary.

95.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,439 - 1,460

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #3 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.8%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

54.8%Raw benchmark valueCI 48.2% - 61.3%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.1%
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

62.1%Raw benchmark valueCI 59.6% - 64.6%

Search / tool use3 benchmarks78%

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 #20 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 94.4%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

93.9% percentile inside its fair comparison set

94.4%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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,194
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #10. Votes: 18408. Organization: anthropic. License: Proprietary.

73.3% percentile inside its fair comparison set

1,194Raw benchmark valueCI 1,188 - 1,201

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,203
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #11. Votes: 18408. Organization: anthropic. License: Proprietary.

66.7% percentile inside its fair comparison set

1,203Raw benchmark valueCI 1,196 - 1,209

Long context2 benchmarks92.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #15 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67.7%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

95.6% percentile inside its fair comparison set

67.7%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 #10 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.7%
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

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

89.8% percentile inside its fair comparison set

66.7%Raw benchmark valueCI 64.9% - 68.5%

Vision understanding13 benchmarks87.2%

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #12. Votes: 4131. Organization: anthropic. License: Proprietary.

92.7% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,269 - 1,291

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,276
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing_vision. Source rank: #14. Votes: 221. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,276Raw benchmark valueCI 1,234 - 1,317

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 #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,300
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: diagram. Source rank: #17. Votes: 1103. Organization: anthropic. License: Proprietary.

82.9% percentile inside its fair comparison set

1,300Raw benchmark valueCI 1,281 - 1,319

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #11. Votes: 1751. Organization: anthropic. License: Proprietary.

92.7% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,263 - 1,294

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: homework. Source rank: #14. Votes: 630. Organization: anthropic. License: Proprietary.

86.8% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,284 - 1,333

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,288
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: ocr. Source rank: #15. Votes: 3020. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,288Raw benchmark valueCI 1,276 - 1,300

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #13. Votes: 4131. Organization: anthropic. License: Proprietary.

91.7% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,279 - 1,300

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing_vision. Source rank: #14. Votes: 221. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,245 - 1,328

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,298
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: diagram. Source rank: #15. Votes: 1103. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,298Raw benchmark valueCI 1,279 - 1,317

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #13. Votes: 1751. Organization: anthropic. License: Proprietary.

90.8% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,274 - 1,305

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: homework. Source rank: #14. Votes: 630. Organization: anthropic. License: Proprietary.

86.8% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,290 - 1,338

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,294
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: ocr. Source rank: #15. Votes: 3020. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,294Raw benchmark valueCI 1,282 - 1,306

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 #10 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.6%
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

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

84.5% percentile inside its fair comparison set

86.6%Raw benchmark valueCI 85% - 88.2%

Document understanding4 benchmarks86.8%

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #7. Votes: 3223. Organization: anthropic. License: Proprietary.

83.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,474 - 1,495

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #11. Votes: 3223. Organization: anthropic. License: Proprietary.

70.8% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,461 - 1,483

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

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

94.7% percentile inside its fair comparison set

71Raw benchmark valueCI 69 - 72

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.9%
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

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

98.3% percentile inside its fair comparison set

69.9%Raw benchmark valueCI 68.2% - 71.7%

Multilingual14 benchmarks93.2%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #10. Votes: 578. Organization: anthropic. License: Proprietary.

97.6% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,501 - 1,552

Text Arena · French

AR · Multilingual · Human

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

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: french. Source rank: #11. Votes: 545. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,476 - 1,531

Text Arena · German

AR · Multilingual · Human

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

Rank #23

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: german. Source rank: #30. Votes: 239. Organization: anthropic. License: Proprietary.

90.7% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,423 - 1,497

Text Arena · Korean

AR · Multilingual · Human

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

Rank #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: korean. Source rank: #5. Votes: 183. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,420 - 1,508

Text Arena · Russian

AR · Multilingual · Human

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

Rank #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: russian. Source rank: #16. Votes: 1380. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,466 - 1,499

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: spanish. Source rank: #5. Votes: 411. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,454 - 1,513

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #20

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 93.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #25. Votes: 578. Organization: anthropic. License: Proprietary.

93.6% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,476 - 1,526

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: french. Source rank: #22. Votes: 545. Organization: anthropic. License: Proprietary.

92.1% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,445 - 1,499

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #36

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: german. Source rank: #45. Votes: 239. Organization: anthropic. License: Proprietary.

85.2% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,396 - 1,471

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: korean. Source rank: #11. Votes: 183. Organization: anthropic. License: Proprietary.

95.7% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,399 - 1,488

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: russian. Source rank: #22. Votes: 1380. Organization: anthropic. License: Proprietary.

94.1% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,444 - 1,477

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: spanish. Source rank: #15. Votes: 411. Organization: anthropic. License: Proprietary.

94.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,434 - 1,493

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #12. Votes: 193. Organization: anthropic. License: Proprietary.

89.6% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,272 - 1,362

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #14

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #18. Votes: 193. Organization: anthropic. License: Proprietary.

83.1% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,285 - 1,375

Source links and registry checks

official

Anthropic model overview

Jun 20, 2026

source →

official

vals-ai

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 4.8

Closed weightsfrontier · registry tag 2026 current

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 34.9%
Verified coverage: 34.9%
Spread: 94.3%
Last verified: Jun 20, 2026

84%bench fit

textcodevisiondocument4 aliases39 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 benchmarks78.8%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

99.7% percentile inside its fair comparison set

56Raw 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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 46.6%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

98.7% percentile inside its fair comparison set

46.6%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 #21 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.1%
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

93.3% percentile inside its fair comparison set

64.1%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 #53 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 62.2%
Percentile: 83.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

83.5% percentile inside its fair comparison set

62.2%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 #261 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #263 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #261 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max 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 #132 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.8 tokens/s
Percentile: 37.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

37.6% percentile inside its fair comparison set

69.8 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 #199 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.32s
Percentile: 5.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

5.7% percentile inside its fair comparison set

33.32sRaw 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 #164 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 33.32s
Percentile: 22.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

22.4% percentile inside its fair comparison set

33.32sRaw 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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #12. Votes: 13316. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,472 - 1,484

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 #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing. Source rank: #16. Votes: 2317. Organization: anthropic. License: Proprietary.

96.3% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,444 - 1,470

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #11. Votes: 6464. Organization: anthropic. License: Proprietary.

97.5% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,493

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: exclude_ties. Source rank: #11. Votes: 9999. Organization: anthropic. License: Proprietary.

97.5% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,497

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts. Source rank: #7. Votes: 8692. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,520

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts_english. Source rank: #6. Votes: 4444. Organization: anthropic. License: Proprietary.

99.1% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,506 - 1,526

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: instruction_following. Source rank: #7. Votes: 4330. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,476 - 1,495

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: longer_query. Source rank: #6. Votes: 5865. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,499 - 1,517

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: multi_turn. Source rank: #7. Votes: 2421. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,487 - 1,512

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #23. Votes: 13316. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,448 - 1,461

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 #21

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing. Source rank: #26. Votes: 2317. Organization: anthropic. License: Proprietary.

93.8% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,424 - 1,450

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #23. Votes: 6464. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,453 - 1,469

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 #19

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: exclude_ties. Source rank: #23. Votes: 9999. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,447 - 1,463

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 #16

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts. Source rank: #20. Votes: 8692. Organization: anthropic. License: Proprietary.

95.4% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,486

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: hard_prompts_english. Source rank: #10. Votes: 4444. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,474 - 1,493

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 #12

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: instruction_following. Source rank: #16. Votes: 4330. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,458 - 1,477

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 #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: longer_query. Source rank: #6. Votes: 5865. Organization: anthropic. License: Proprietary.

99% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: multi_turn. Source rank: #14. Votes: 2421. Organization: anthropic. License: Proprietary.

96.9% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,464 - 1,489

Coding16 benchmarks96.2%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 58.3%
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

99.7% percentile inside its fair comparison set

58.3%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 #3 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53.5%
Percentile: 99.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

99.5% percentile inside its fair comparison set

53.5%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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 74
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

98.7% 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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

97.8% percentile inside its fair comparison set

47Raw 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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #6. Votes: 3441. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,531 - 1,553

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 94.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev. Source rank: #6. Votes: 3441. Organization: anthropic. License: Proprietary.

94.5% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,531 - 1,553

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 #6

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,529
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev-html. Source rank: #8. Votes: 484. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,529Raw benchmark valueCI 1,501 - 1,557

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,541
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: webdev-react. Source rank: #6. Votes: 2950. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,541Raw benchmark valueCI 1,529 - 1,552

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.3%
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

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

95.5% percentile inside its fair comparison set

47.3%Raw benchmark valueCI 39.1% - 55.4%

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 #4 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.8%
Percentile: 96.7%
Last updated: recent
Eligibility: headline eligible

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

96.7% percentile inside its fair comparison set

87.8%Raw benchmark valueCI 86% - 89.7%

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1%
Percentile: 95%
Last updated: recent
Eligibility: headline eligible

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

95% percentile inside its fair comparison set

1%Raw benchmark valueCI 0% - 2.4%

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.6%
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

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

98.1% percentile inside its fair comparison set

88.6%Raw benchmark valueCI 85.8% - 91.4%

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 #4 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.9%
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

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

88.9% percentile inside its fair comparison set

71.9%Raw benchmark valueCI 70.6% - 73.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.7%
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

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

98% percentile inside its fair comparison set

82.7%Raw benchmark valueCI 76.7% - 88.8%

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,540
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: coding. Source rank: #7. Votes: 3592. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,540Raw benchmark valueCI 1,529 - 1,550

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: coding. Source rank: #14. Votes: 3592. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,486 - 1,507

Reasoning / math / science8 benchmarks97.5%

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 #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.7%
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

99.7% percentile inside its fair comparison set

45.7%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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 92%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

98.9% percentile inside its fair comparison set

92%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 #5 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 20.9%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

98.7% percentile inside its fair comparison set

20.9%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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69%
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

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

97.1% percentile inside its fair comparison set

69%Raw benchmark valueCI 59.9% - 78.1%

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 #6 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 92.4%
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

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

94.4% percentile inside its fair comparison set

92.4%Raw benchmark valueCI 88.5% - 96.3%

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 #5 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

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

95.5% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 89% - 90.2%

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 #7

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: math. Source rank: #9. Votes: 648. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,473 - 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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: math. Source rank: #11. Votes: 648. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,465 - 1,510

Professional reasoning31 benchmarks94.6%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #2 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,605
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

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

97.8% percentile inside its fair comparison set

1,605Raw benchmark value

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #1 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.8%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

43.8%Raw benchmark valueCI 37% - 50.5%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.2%
Percentile: 90%
Last updated: recent
Eligibility: headline eligible

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

90% percentile inside its fair comparison set

59.2%Raw benchmark valueCI 50.4% - 68%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #1 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.1%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

68.1%Raw benchmark valueCI 65.8% - 70.5%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

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

96.2% percentile inside its fair comparison set

70Raw benchmark valueCI 69 - 72

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 9.6%
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

9.6%Raw benchmark valueCI 5.4% - 13.8%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #30 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.6%
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

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

67.8% percentile inside its fair comparison set

83.6%Raw benchmark valueCI 82.6% - 84.5%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #3 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.9%
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

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

92% percentile inside its fair comparison set

53.9%Raw benchmark valueCI 53.6% - 54.2%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #8 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.6%
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

75.6%Raw benchmark valueCI 74% - 77.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #6 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.2%
Percentile: 90.2%
Last updated: recent
Eligibility: headline eligible

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

90.2% percentile inside its fair comparison set

53.2%Raw benchmark valueCI 49% - 57.5%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #7 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.8%
Percentile: 88%
Last updated: recent
Eligibility: headline eligible

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

88% percentile inside its fair comparison set

85.8%Raw benchmark valueCI 82% - 89.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: expert. Source rank: #5. Votes: 1258. Organization: anthropic. License: Proprietary.

98.9% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,513 - 1,547

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 #3

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

99.4% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,488 - 1,512

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,457
Percentile: 97.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 2946. Organization: anthropic. License: Proprietary.

97.8% percentile inside its fair comparison set

1,457Raw benchmark valueCI 1,446 - 1,469

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #3

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_legal_and_government. Source rank: #3. Votes: 1020. Organization: anthropic. License: Proprietary.

99.3% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,490 - 1,530

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_life_and_physical_and_social_science. Source rank: #12. Votes: 2213. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,484 - 1,510

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_mathematical. Source rank: #9. Votes: 668. Organization: anthropic. License: Proprietary.

97.7% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,479 - 1,525

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_medicine_and_healthcare. Source rank: #13. Votes: 982. Organization: anthropic. License: Proprietary.

96.6% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,479 - 1,518

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_software_and_it_services. Source rank: #7. Votes: 5156. Organization: anthropic. License: Proprietary.

98.8% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,515 - 1,533

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,467
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_writing_and_literature_and_language. Source rank: #13. Votes: 3391. Organization: anthropic. License: Proprietary.

97.2% percentile inside its fair comparison set

1,467Raw benchmark valueCI 1,456 - 1,477

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: expert. Source rank: #11. Votes: 1258. Organization: anthropic. License: Proprietary.

97.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,486 - 1,520

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

97.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,450 - 1,475

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 #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_entertainment_and_sports_and_media. Source rank: #22. Votes: 2946. Organization: anthropic. License: Proprietary.

94.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,445

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_legal_and_government. Source rank: #10. Votes: 1020. Organization: anthropic. License: Proprietary.

97.3% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,463 - 1,502

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 #23

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 93.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_life_and_physical_and_social_science. Source rank: #28. Votes: 2213. Organization: anthropic. License: Proprietary.

93.2% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,452 - 1,478

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_mathematical. Source rank: #11. Votes: 668. Organization: anthropic. License: Proprietary.

97.4% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,469 - 1,515

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 #37

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 87.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_medicine_and_healthcare. Source rank: #40. Votes: 982. Organization: anthropic. License: Proprietary.

87.8% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,436 - 1,474

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 #14

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_software_and_it_services. Source rank: #17. Votes: 5156. Organization: anthropic. License: Proprietary.

96% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,478 - 1,496

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 #17

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 95.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: industry_writing_and_literature_and_language. Source rank: #21. Votes: 3391. Organization: anthropic. License: Proprietary.

95.1% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,439 - 1,460

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #3 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.8%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

54.8%Raw benchmark valueCI 48.2% - 61.3%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.1%
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

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

91.7% percentile inside its fair comparison set

62.1%Raw benchmark valueCI 59.6% - 64.6%

Search / tool use3 benchmarks78%

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 #20 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 94.4%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

93.9% percentile inside its fair comparison set

94.4%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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,194
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #10. Votes: 18408. Organization: anthropic. License: Proprietary.

73.3% percentile inside its fair comparison set

1,194Raw benchmark valueCI 1,188 - 1,201

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,203
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #11. Votes: 18408. Organization: anthropic. License: Proprietary.

66.7% percentile inside its fair comparison set

1,203Raw benchmark valueCI 1,196 - 1,209

Long context2 benchmarks92.7%

Long Context Reasoning

AA · Long context · Objective

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

Rank #15 · Source label: Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 67.7%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

95.6% percentile inside its fair comparison set

67.7%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 #10 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.7%
Percentile: 89.8%
Last updated: recent
Eligibility: headline eligible

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

89.8% percentile inside its fair comparison set

66.7%Raw benchmark valueCI 64.9% - 68.5%

Vision understanding13 benchmarks87.2%

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #12. Votes: 4131. Organization: anthropic. License: Proprietary.

92.7% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,269 - 1,291

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,276
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing_vision. Source rank: #14. Votes: 221. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,276Raw benchmark valueCI 1,234 - 1,317

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 #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,300
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: diagram. Source rank: #17. Votes: 1103. Organization: anthropic. License: Proprietary.

82.9% percentile inside its fair comparison set

1,300Raw benchmark valueCI 1,281 - 1,319

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 #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,278
Percentile: 92.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #11. Votes: 1751. Organization: anthropic. License: Proprietary.

92.7% percentile inside its fair comparison set

1,278Raw benchmark valueCI 1,263 - 1,294

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: homework. Source rank: #14. Votes: 630. Organization: anthropic. License: Proprietary.

86.8% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,284 - 1,333

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,288
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: ocr. Source rank: #15. Votes: 3020. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,288Raw benchmark valueCI 1,276 - 1,300

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #13. Votes: 4131. Organization: anthropic. License: Proprietary.

91.7% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,279 - 1,300

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,287
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: creative_writing_vision. Source rank: #14. Votes: 221. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,287Raw benchmark valueCI 1,245 - 1,328

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,298
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: diagram. Source rank: #15. Votes: 1103. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,298Raw benchmark valueCI 1,279 - 1,317

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 90.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: english. Source rank: #13. Votes: 1751. Organization: anthropic. License: Proprietary.

90.8% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,274 - 1,305

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 #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: homework. Source rank: #14. Votes: 630. Organization: anthropic. License: Proprietary.

86.8% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,290 - 1,338

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 #11

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,294
Percentile: 85.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: ocr. Source rank: #15. Votes: 3020. Organization: anthropic. License: Proprietary.

85.7% percentile inside its fair comparison set

1,294Raw benchmark valueCI 1,282 - 1,306

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 #10 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.6%
Percentile: 84.5%
Last updated: recent
Eligibility: headline eligible

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

84.5% percentile inside its fair comparison set

86.6%Raw benchmark valueCI 85% - 88.2%

Document understanding4 benchmarks86.8%

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 #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #7. Votes: 3223. Organization: anthropic. License: Proprietary.

83.3% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,474 - 1,495

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 #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 70.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: overall. Source rank: #11. Votes: 3223. Organization: anthropic. License: Proprietary.

70.8% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,461 - 1,483

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71
Percentile: 94.7%
Last updated: recent
Eligibility: headline eligible

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

94.7% percentile inside its fair comparison set

71Raw benchmark valueCI 69 - 72

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 #2 · Source label: anthropic/claude-opus-4-8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.9%
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

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

98.3% percentile inside its fair comparison set

69.9%Raw benchmark valueCI 68.2% - 71.7%

Multilingual14 benchmarks93.2%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #8

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #10. Votes: 578. Organization: anthropic. License: Proprietary.

97.6% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,501 - 1,552

Text Arena · French

AR · Multilingual · Human

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

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: french. Source rank: #11. Votes: 545. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,476 - 1,531

Text Arena · German

AR · Multilingual · Human

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

Rank #23

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 90.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: german. Source rank: #30. Votes: 239. Organization: anthropic. License: Proprietary.

90.7% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,423 - 1,497

Text Arena · Korean

AR · Multilingual · Human

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

Rank #5

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: korean. Source rank: #5. Votes: 183. Organization: anthropic. License: Proprietary.

98.1% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,420 - 1,508

Text Arena · Russian

AR · Multilingual · Human

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

Rank #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: russian. Source rank: #16. Votes: 1380. Organization: anthropic. License: Proprietary.

95.8% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,466 - 1,499

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #4

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: spanish. Source rank: #5. Votes: 411. Organization: anthropic. License: Proprietary.

98.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,454 - 1,513

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #20

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 93.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #25. Votes: 578. Organization: anthropic. License: Proprietary.

93.6% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,476 - 1,526

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: french. Source rank: #22. Votes: 545. Organization: anthropic. License: Proprietary.

92.1% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,445 - 1,499

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #36

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 85.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: german. Source rank: #45. Votes: 239. Organization: anthropic. License: Proprietary.

85.2% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,396 - 1,471

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #10

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: korean. Source rank: #11. Votes: 183. Organization: anthropic. License: Proprietary.

95.7% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,399 - 1,488

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #18

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,460
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: russian. Source rank: #22. Votes: 1380. Organization: anthropic. License: Proprietary.

94.1% percentile inside its fair comparison set

1,460Raw benchmark valueCI 1,444 - 1,477

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #13

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: spanish. Source rank: #15. Votes: 411. Organization: anthropic. License: Proprietary.

94.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,434 - 1,493

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #9

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #12. Votes: 193. Organization: anthropic. License: Proprietary.

89.6% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,272 - 1,362

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #14

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 83.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-opus-4-8`. Category: chinese. Source rank: #18. Votes: 193. Organization: anthropic. License: Proprietary.

83.1% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,285 - 1,375