Model profile · Anthropic

Claude Haiku 4.5

Closed weightsmid · registry tag 2026 fast

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 53.4%
Verified coverage: 52.7%
Spread: 97.7%
Last verified: Jun 20, 2026

35%bench fit

textvisiondocumentcode7 aliases36 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 / text38 benchmarks54.5%

Intelligence Index

AA · Chat / text · Combined

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

Rank #91 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

77.2% percentile inside its fair comparison set

24Raw 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 #211 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.7%
Percentile: 29.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

29.5% percentile inside its fair comparison set

13.7%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 #5 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.3%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

98.7% percentile inside its fair comparison set

75.3%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 #150 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42%
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

52.7% percentile inside its fair comparison set

42%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 #206 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M tokens
Percentile: 25.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

25.7% percentile inside its fair comparison set

$2 /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 #197 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1 /1M input tokens
Percentile: 29%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

29% percentile inside its fair comparison set

$1 /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 #210 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M output tokens
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

24.6% percentile inside its fair comparison set

$5 /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 #102 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 96.8 tokens/s
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.9% percentile inside its fair comparison set

96.8 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 #27 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.89s
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

87.6% percentile inside its fair comparison set

0.89sRaw 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 #18 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.89s
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

91.9% percentile inside its fair comparison set

0.89sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #158 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11
Percentile: 15.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

15.6% percentile inside its fair comparison set

11Raw 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 #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #106. Votes: 91153. Organization: anthropic. License: Proprietary.

73.8% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,408 - 1,414

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 #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: creative_writing. Source rank: #96. Votes: 13641. Organization: anthropic. License: Proprietary.

76.2% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,381 - 1,392

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 #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 78.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: english. Source rank: #89. Votes: 43281. Organization: anthropic. License: Proprietary.

78.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

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 #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: exclude_ties. Source rank: #106. Votes: 67483. Organization: anthropic. License: Proprietary.

73.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,394 - 1,402

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 #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts. Source rank: #91. Votes: 53244. Organization: anthropic. License: Proprietary.

77.8% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,435 - 1,443

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 #63 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 80.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts_english. Source rank: #79. Votes: 26560. Organization: anthropic. License: Proprietary.

80.9% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,450 - 1,459

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 #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: instruction_following. Source rank: #86. Votes: 26995. Organization: anthropic. License: Proprietary.

79.1% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,410 - 1,419

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 #61 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 80.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: longer_query. Source rank: #76. Votes: 29096. Organization: anthropic. License: Proprietary.

80.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,441

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 #68 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 79.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: multi_turn. Source rank: #86. Votes: 16101. Organization: anthropic. License: Proprietary.

79.3% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,420 - 1,431

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 #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #122. Votes: 91153. Organization: anthropic. License: Proprietary.

69.2% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,389 - 1,395

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 #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,369
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: creative_writing. Source rank: #102. Votes: 13641. Organization: anthropic. License: Proprietary.

74.9% percentile inside its fair comparison set

1,369Raw benchmark valueCI 1,363 - 1,375

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 #92 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 72%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: english. Source rank: #108. Votes: 43281. Organization: anthropic. License: Proprietary.

72% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,417

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 #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: exclude_ties. Source rank: #122. Votes: 67483. Organization: anthropic. License: Proprietary.

69.2% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,367 - 1,374

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 #80 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts. Source rank: #97. Votes: 53244. Organization: anthropic. License: Proprietary.

75.7% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,413 - 1,420

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 #65 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 80.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts_english. Source rank: #80. Votes: 26560. Organization: anthropic. License: Proprietary.

80.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,429 - 1,439

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 #50 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 84.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: instruction_following. Source rank: #63. Votes: 26995. Organization: anthropic. License: Proprietary.

84.9% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,407 - 1,416

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 #49 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: longer_query. Source rank: #61. Votes: 29096. Organization: anthropic. License: Proprietary.

84.2% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,432

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 #81 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 75.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: multi_turn. Source rank: #98. Votes: 16101. Organization: anthropic. License: Proprietary.

75.2% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,403 - 1,414

Instruction following

LB · Chat / text · Objective

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

Rank #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 17.8%
Percentile: 4.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

4.6% percentile inside its fair comparison set

17.8%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 20.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

20.4% percentile inside its fair comparison set

57%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #103 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 15.5%
Percentile: 5.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

5.6% percentile inside its fair comparison set

15.5%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #103 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19%
Percentile: 5.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

5.6% percentile inside its fair comparison set

19%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.4%
Percentile: 4.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

4.6% percentile inside its fair comparison set

16.4%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #105 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.2%
Percentile: 3.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

3.7% percentile inside its fair comparison set

20.2%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.3%
Percentile: 21.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

21.3% percentile inside its fair comparison set

71.3%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 37.8%
Percentile: 18.5%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

18.5% percentile inside its fair comparison set

37.8%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #91 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 16.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

16.8% percentile inside its fair comparison set

62%Raw benchmark value

Coding23 benchmarks38.3%

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 #73 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 27.3%
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

76.2% percentile inside its fair comparison set

27.3%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 #138 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34.4%
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

63% percentile inside its fair comparison set

34.4%Raw 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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #68. Votes: 22687. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,320 - 1,331

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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev. Source rank: #68. Votes: 22687. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,320 - 1,331

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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev-html. Source rank: #68. Votes: 11943. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,305 - 1,323

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 #46 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,328
Percentile: 23.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev-react. Source rank: #58. Votes: 10707. Organization: anthropic. License: Proprietary.

23.7% percentile inside its fair comparison set

1,328Raw benchmark valueCI 1,321 - 1,335

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 #20 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 7.6%
Percentile: 13.6%
Last updated: recent
Eligibility: headline eligible

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

13.6% percentile inside its fair comparison set

7.6%Raw benchmark valueCI 5.5% - 9.6%

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 #82 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.2%
Percentile: 10%
Last updated: recent
Eligibility: headline eligible

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

10% percentile inside its fair comparison set

41.2%Raw benchmark valueCI 39% - 43.3%

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 #18 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #43 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.6%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

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

22.2% percentile inside its fair comparison set

66.6%Raw benchmark valueCI 62.5% - 70.7%

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 #24 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.8%
Percentile: 14.8%
Last updated: recent
Eligibility: headline eligible

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

14.8% percentile inside its fair comparison set

43.8%Raw benchmark valueCI 40% - 47.6%

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 #40 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.4%
Percentile: 20.4%
Last updated: recent
Eligibility: headline eligible

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

20.4% percentile inside its fair comparison set

11.4%Raw benchmark valueCI 5.3% - 17.5%

Text Arena · Coding

AR · Coding · Human

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

Rank #56 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 82.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: coding. Source rank: #70. Votes: 22112. Organization: anthropic. License: Proprietary.

82.8% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,474 - 1,484

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 #51 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: coding. Source rank: #61. Votes: 22112. Organization: anthropic. License: Proprietary.

84.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,455

IOI

VALS-AI · Coding · Objective

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

Rank #32 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 6.2%
Percentile: 29.5%
Last updated: recent
Eligibility: headline eligible

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

29.5% percentile inside its fair comparison set

6.2%Raw benchmark valueCI 1.2% - 11.1%

Agentic coding

LB · Coding · Objective

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

Rank #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.3%
Percentile: 28.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

28.7% percentile inside its fair comparison set

33.3%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #63 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.2%
Percentile: 42.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

42.6% percentile inside its fair comparison set

72.2%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 30%
Percentile: 38%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

38% percentile inside its fair comparison set

30%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 37.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

37.4% percentile inside its fair comparison set

25%Raw benchmark value

Python

LB · Coding · Objective

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

Rank #81 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 25.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

25.9% percentile inside its fair comparison set

45%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #79 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.4%
Percentile: 28.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

28.7% percentile inside its fair comparison set

70.4%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #43 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 61.1%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

61.1% percentile inside its fair comparison set

73.9%Raw benchmark value

Terminal-Bench 2.0

TERMINAL-BENCH · Coding · Objective

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

Rank #22 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 29.8%
Percentile: 30%
Last updated: archived
Eligibility: headline eligible

Parsed from the public Terminal-Bench 2.0 verified leaderboard. Collapse policy: highest verified score per canonical model. Selected agent: Mini-SWE-Agent (unknown). Display model: Claude Haiku 4.5. Integration method: API. Agent URL: https://github.com/SWE-agent/mini-swe-agent. Reported stderr: 1.282 percentage points.

30% percentile inside its fair comparison set

29.8%Raw benchmark value

Reasoning / math / science17 benchmarks27.5%

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 #289 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.3%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

22.2% percentile inside its fair comparison set

4.3%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #177 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.6%
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

52.9% percentile inside its fair comparison set

64.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #137 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

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 #59 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.2%
Percentile: 34.8%
Last updated: recent
Eligibility: headline eligible

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

34.8% percentile inside its fair comparison set

72.2%Raw benchmark valueCI 67.4% - 77.1%

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 #66 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.7%
Percentile: 27%
Last updated: recent
Eligibility: headline eligible

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

27% percentile inside its fair comparison set

78.7%Raw benchmark valueCI 77.8% - 79.6%

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 #102 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: math. Source rank: #125. Votes: 5407. Organization: anthropic. License: Proprietary.

67.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,389 - 1,406

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 #108 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: math. Source rank: #128. Votes: 5407. Organization: anthropic. License: Proprietary.

65.9% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,383 - 1,400

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #97 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58%
Percentile: 11.1%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

11.1% percentile inside its fair comparison set

58%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.9%
Percentile: 7.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

7.4% percentile inside its fair comparison set

33.9%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #80 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 26.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

26.9% percentile inside its fair comparison set

88%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #108 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 4%
Percentile: 0.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

0.9% percentile inside its fair comparison set

4%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #98 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.6%
Percentile: 10.2%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

10.2% percentile inside its fair comparison set

68.6%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.3%
Percentile: 20.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

20.4% percentile inside its fair comparison set

71.3%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #79 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 27.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

27.8% percentile inside its fair comparison set

50%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #97 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 9.8%
Percentile: 10.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

10.3% percentile inside its fair comparison set

9.8%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58%
Percentile: 7.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

7.4% percentile inside its fair comparison set

58%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18%
Percentile: 9.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

9.3% percentile inside its fair comparison set

18%Raw benchmark value

Professional reasoning32 benchmarks52.6%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #9 · Source label: anthropic/claude-haiku-4-5-20251001

verified runtimevariant direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.3%
Percentile: 27.3%
Last updated: recent
Eligibility: headline eligible

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

27.3% percentile inside its fair comparison set

54.3%Raw benchmark valueCI 51.7% - 56.8%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #24 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41
Percentile: 11.5%
Last updated: recent
Eligibility: headline eligible

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

11.5% percentile inside its fair comparison set

41Raw benchmark valueCI 39 - 43

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #49 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.2%
Percentile: 46.7%
Last updated: recent
Eligibility: headline eligible

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

46.7% percentile inside its fair comparison set

81.2%Raw benchmark valueCI 80.3% - 82.2%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #23 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31%
Percentile: 12%
Last updated: recent
Eligibility: headline eligible

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

12% percentile inside its fair comparison set

31%Raw benchmark valueCI 29.9% - 32.1%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #70 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.5%
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible

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

24.2% percentile inside its fair comparison set

67.5%Raw benchmark valueCI 65.7% - 69.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #46 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 32.7%
Percentile: 11.8%
Last updated: recent
Eligibility: headline eligible

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

11.8% percentile inside its fair comparison set

32.7%Raw benchmark valueCI 28.8% - 36.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #9 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.2%
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

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

84% percentile inside its fair comparison set

85.2%Raw benchmark valueCI 81.5% - 89%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #53 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: expert. Source rank: #69. Votes: 6618. Organization: anthropic. License: Proprietary.

81.1% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,447 - 1,464

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 #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 78%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_business_and_management_and_financial_operations. Source rank: #88. Votes: 17395. Organization: anthropic. License: Proprietary.

78% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,411 - 1,422

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 #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_entertainment_and_sports_and_media. Source rank: #97. Votes: 17599. Organization: anthropic. License: Proprietary.

76.2% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,379 - 1,390

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_legal_and_government. Source rank: #111. Votes: 6567. Organization: anthropic. License: Proprietary.

70.5% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,406 - 1,422

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 #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_life_and_physical_and_social_science. Source rank: #104. Votes: 14574. Organization: anthropic. License: Proprietary.

74.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,424 - 1,435

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #70 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 77.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_mathematical. Source rank: #85. Votes: 4472. Organization: anthropic. License: Proprietary.

77.6% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,420 - 1,439

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_medicine_and_healthcare. Source rank: #123. Votes: 5734. Organization: anthropic. License: Proprietary.

66.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,411 - 1,429

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 #62 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 81.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_software_and_it_services. Source rank: #78. Votes: 33588. Organization: anthropic. License: Proprietary.

81.2% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,457 - 1,466

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 #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_writing_and_literature_and_language. Source rank: #91. Votes: 20720. Organization: anthropic. License: Proprietary.

77.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #46 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: expert. Source rank: #54. Votes: 6618. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,435 - 1,451

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 #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 73%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_business_and_management_and_financial_operations. Source rank: #105. Votes: 17395. Organization: anthropic. License: Proprietary.

73% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,390 - 1,401

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 #90 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,363
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_entertainment_and_sports_and_media. Source rank: #110. Votes: 17599. Organization: anthropic. License: Proprietary.

72.4% percentile inside its fair comparison set

1,363Raw benchmark valueCI 1,358 - 1,369

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 #100 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_legal_and_government. Source rank: #121. Votes: 6567. Organization: anthropic. License: Proprietary.

66.8% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,388 - 1,404

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 #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_life_and_physical_and_social_science. Source rank: #123. Votes: 14574. Organization: anthropic. License: Proprietary.

68.1% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,407

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 77.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_mathematical. Source rank: #84. Votes: 4472. Organization: anthropic. License: Proprietary.

77.3% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,413 - 1,432

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 #111 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 62.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_medicine_and_healthcare. Source rank: #134. Votes: 5734. Organization: anthropic. License: Proprietary.

62.7% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,377 - 1,394

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 #75 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_software_and_it_services. Source rank: #90. Votes: 33588. Organization: anthropic. License: Proprietary.

77.2% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,431 - 1,439

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 #85 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_writing_and_literature_and_language. Source rank: #103. Votes: 20720. Organization: anthropic. License: Proprietary.

74.1% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,379 - 1,389

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #37 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.8%
Percentile: 20%
Last updated: recent
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

31.8%Raw benchmark valueCI 25.7% - 38%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #12 · Source label: anthropic/claude-haiku-4-5-20251001

verified runtimevariant direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.5%
Percentile: 8.3%
Last updated: recent
Eligibility: headline eligible

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

8.3% percentile inside its fair comparison set

49.5%Raw benchmark valueCI 47% - 52.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #88 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.1%
Percentile: 19.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

19.4% percentile inside its fair comparison set

45.1%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #93 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.3%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

14.8% percentile inside its fair comparison set

45.3%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #90 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3%
Percentile: 17.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

17.6% percentile inside its fair comparison set

3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #75 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 38.3%
Percentile: 31.5%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

31.5% percentile inside its fair comparison set

38.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #96 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.1%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

14.8% percentile inside its fair comparison set

94.1%Raw benchmark value

Search / tool use1 benchmark46%

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 #168 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.5%
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

46% percentile inside its fair comparison set

32.5%Raw benchmark value

Long context2 benchmarks56%

Long Context Reasoning

AA · Long context · Objective

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

Rank #111 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.7%
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

65.4% percentile inside its fair comparison set

43.7%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 #48 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.6%
Percentile: 46.6%
Last updated: recent
Eligibility: headline eligible

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

46.6% percentile inside its fair comparison set

60.6%Raw benchmark valueCI 58.7% - 62.5%

Vision understanding12 benchmarks15.2%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #88 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.1%
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

35.6% percentile inside its fair comparison set

55.1%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #75 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 33%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: overall. Source rank: #93. Votes: 1430. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

33% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,110 - 1,142

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 #68 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,130
Percentile: 5.7%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: diagram. Source rank: #84. Votes: 325. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

5.7% percentile inside its fair comparison set

1,130Raw benchmark valueCI 1,097 - 1,163

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 #76 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 32.1%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: english. Source rank: #94. Votes: 685. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

32.1% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,103 - 1,148

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 #67 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,142
Percentile: 4.4%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: homework. Source rank: #82. Votes: 232. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

4.4% percentile inside its fair comparison set

1,142Raw benchmark valueCI 1,105 - 1,180

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: ocr. Source rank: #86. Votes: 934. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

2.9% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,107 - 1,146

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 #78 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,092
Percentile: 30.3%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: overall. Source rank: #96. Votes: 1430. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

30.3% percentile inside its fair comparison set

1,092Raw benchmark valueCI 1,076 - 1,108

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,078
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: diagram. Source rank: #86. Votes: 325. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

2.9% percentile inside its fair comparison set

1,078Raw benchmark valueCI 1,045 - 1,111

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 #81 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,097
Percentile: 27.5%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: english. Source rank: #99. Votes: 685. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

27.5% percentile inside its fair comparison set

1,097Raw benchmark valueCI 1,074 - 1,119

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 #68 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,116
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

Parsed from Arena leaderboard dataset row `claude-3-5-haiku-20241022`. Category: homework. Source rank: #83. Votes: 232. Organization: anthropic. License: Proprietary. Backfilled from Claude Haiku 3.5 via approved benchmark identity mapping map-claude-haiku-4-5-to-3-5.

2.9% percentile inside its fair comparison set

1,116Raw benchmark valueCI 1,079 - 1,154

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,089
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

2.9% percentile inside its fair comparison set

1,089Raw benchmark valueCI 1,069 - 1,108

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 #58 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 46.1%
Percentile: 1.7%
Last updated: recent
Eligibility: headline eligible

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

1.7% percentile inside its fair comparison set

46.1%Raw benchmark valueCI 43.7% - 48.4%

Document understanding4 benchmarks23.5%

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 #23 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 8.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #27. Votes: 26371. Organization: anthropic. License: Proprietary.

8.3% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,410 - 1,423

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 #19 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #22. Votes: 26371. Organization: anthropic. License: Proprietary.

25% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,412 - 1,425

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 #17 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43
Percentile: 15.8%
Last updated: recent
Eligibility: headline eligible

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

15.8% percentile inside its fair comparison set

43Raw benchmark valueCI 41 - 45

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 #34 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.2%
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

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

45% percentile inside its fair comparison set

62.2%Raw benchmark valueCI 60.3% - 64%

Multilingual14 benchmarks65.6%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #88 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: chinese. Source rank: #110. Votes: 4491. Organization: anthropic. License: Proprietary.

70.5% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,445

Text Arena · French

AR · Multilingual · Human

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

Rank #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: french. Source rank: #100. Votes: 2195. Organization: anthropic. License: Proprietary.

62.5% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,410 - 1,441

Text Arena · German

AR · Multilingual · Human

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

Rank #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: german. Source rank: #92. Votes: 1484. Organization: anthropic. License: Proprietary.

69.6% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,383 - 1,417

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #72 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,351
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: japanese. Source rank: #92. Votes: 766. Organization: anthropic. License: Proprietary.

65% percentile inside its fair comparison set

1,351Raw benchmark valueCI 1,327 - 1,375

Text Arena · Korean

AR · Multilingual · Human

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

Rank #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,356
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: korean. Source rank: #92. Votes: 1336. Organization: anthropic. License: Proprietary.

65.4% percentile inside its fair comparison set

1,356Raw benchmark valueCI 1,338 - 1,374

Text Arena · Russian

AR · Multilingual · Human

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

Rank #91 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: russian. Source rank: #112. Votes: 8599. Organization: anthropic. License: Proprietary.

68.9% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,404

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #52 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: spanish. Source rank: #65. Votes: 2342. Organization: anthropic. License: Proprietary.

76.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,411 - 1,440

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: chinese. Source rank: #121. Votes: 4491. Organization: anthropic. License: Proprietary.

66.8% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,410 - 1,430

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: french. Source rank: #107. Votes: 2195. Organization: anthropic. License: Proprietary.

59.3% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,391 - 1,421

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #95 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: german. Source rank: #116. Votes: 1484. Organization: anthropic. License: Proprietary.

60.3% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,355 - 1,388

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 60.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: japanese. Source rank: #102. Votes: 766. Organization: anthropic. License: Proprietary.

60.1% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,303 - 1,350

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: korean. Source rank: #109. Votes: 1336. Organization: anthropic. License: Proprietary.

57.7% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,316 - 1,352

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: russian. Source rank: #121. Votes: 8599. Organization: anthropic. License: Proprietary.

66.1% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,369 - 1,383

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: spanish. Source rank: #79. Votes: 2342. Organization: anthropic. License: Proprietary.

70.1% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,401 - 1,429

Source links and registry checks

official

Anthropic model overview

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

official

LiveBench

Jun 20, 2026

source →

official

Terminal-Bench

Jun 20, 2026

source →

Model profile · Anthropic

Claude Haiku 4.5

Closed weightsmid · registry tag 2026 fast

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 53.4%
Verified coverage: 52.7%
Spread: 97.7%
Last verified: Jun 20, 2026

35%bench fit

textvisiondocumentcode7 aliases36 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 / text38 benchmarks54.5%

Intelligence Index

AA · Chat / text · Combined

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

Rank #91 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

77.2% percentile inside its fair comparison set

24Raw 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 #211 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.7%
Percentile: 29.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

29.5% percentile inside its fair comparison set

13.7%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 #5 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.3%
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

98.7% percentile inside its fair comparison set

75.3%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 #150 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 42%
Percentile: 52.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

52.7% percentile inside its fair comparison set

42%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 #206 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M tokens
Percentile: 25.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

25.7% percentile inside its fair comparison set

$2 /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 #197 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1 /1M input tokens
Percentile: 29%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

29% percentile inside its fair comparison set

$1 /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 #210 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $5 /1M output tokens
Percentile: 24.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

24.6% percentile inside its fair comparison set

$5 /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 #102 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 96.8 tokens/s
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

51.9% percentile inside its fair comparison set

96.8 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 #27 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.89s
Percentile: 87.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

87.6% percentile inside its fair comparison set

0.89sRaw 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 #18 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.89s
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

91.9% percentile inside its fair comparison set

0.89sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #158 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11
Percentile: 15.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

15.6% percentile inside its fair comparison set

11Raw 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 #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #106. Votes: 91153. Organization: anthropic. License: Proprietary.

73.8% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,408 - 1,414

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 #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: creative_writing. Source rank: #96. Votes: 13641. Organization: anthropic. License: Proprietary.

76.2% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,381 - 1,392

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 #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 78.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: english. Source rank: #89. Votes: 43281. Organization: anthropic. License: Proprietary.

78.5% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,435

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 #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 73.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: exclude_ties. Source rank: #106. Votes: 67483. Organization: anthropic. License: Proprietary.

73.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,394 - 1,402

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 #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts. Source rank: #91. Votes: 53244. Organization: anthropic. License: Proprietary.

77.8% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,435 - 1,443

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 #63 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 80.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts_english. Source rank: #79. Votes: 26560. Organization: anthropic. License: Proprietary.

80.9% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,450 - 1,459

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 #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 79.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: instruction_following. Source rank: #86. Votes: 26995. Organization: anthropic. License: Proprietary.

79.1% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,410 - 1,419

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 #61 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 80.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: longer_query. Source rank: #76. Votes: 29096. Organization: anthropic. License: Proprietary.

80.3% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,432 - 1,441

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 #68 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 79.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: multi_turn. Source rank: #86. Votes: 16101. Organization: anthropic. License: Proprietary.

79.3% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,420 - 1,431

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 #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #122. Votes: 91153. Organization: anthropic. License: Proprietary.

69.2% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,389 - 1,395

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 #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,369
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: creative_writing. Source rank: #102. Votes: 13641. Organization: anthropic. License: Proprietary.

74.9% percentile inside its fair comparison set

1,369Raw benchmark valueCI 1,363 - 1,375

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 #92 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 72%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: english. Source rank: #108. Votes: 43281. Organization: anthropic. License: Proprietary.

72% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,409 - 1,417

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 #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 69.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: exclude_ties. Source rank: #122. Votes: 67483. Organization: anthropic. License: Proprietary.

69.2% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,367 - 1,374

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 #80 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts. Source rank: #97. Votes: 53244. Organization: anthropic. License: Proprietary.

75.7% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,413 - 1,420

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 #65 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 80.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: hard_prompts_english. Source rank: #80. Votes: 26560. Organization: anthropic. License: Proprietary.

80.2% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,429 - 1,439

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 #50 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 84.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: instruction_following. Source rank: #63. Votes: 26995. Organization: anthropic. License: Proprietary.

84.9% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,407 - 1,416

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 #49 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: longer_query. Source rank: #61. Votes: 29096. Organization: anthropic. License: Proprietary.

84.2% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,423 - 1,432

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 #81 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 75.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: multi_turn. Source rank: #98. Votes: 16101. Organization: anthropic. License: Proprietary.

75.2% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,403 - 1,414

Instruction following

LB · Chat / text · Objective

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

Rank #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 17.8%
Percentile: 4.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

4.6% percentile inside its fair comparison set

17.8%Raw benchmark value

Language

LB · Chat / text · Objective

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

Rank #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 57%
Percentile: 20.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

20.4% percentile inside its fair comparison set

57%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

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

Rank #103 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 15.5%
Percentile: 5.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

5.6% percentile inside its fair comparison set

15.5%Raw benchmark value

Simplify

LB · Chat / text · Objective

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

Rank #103 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 19%
Percentile: 5.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

5.6% percentile inside its fair comparison set

19%Raw benchmark value

Story generation

LB · Chat / text · Objective

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

Rank #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 16.4%
Percentile: 4.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

4.6% percentile inside its fair comparison set

16.4%Raw benchmark value

Summarize

LB · Chat / text · Objective

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

Rank #105 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.2%
Percentile: 3.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

3.7% percentile inside its fair comparison set

20.2%Raw benchmark value

Connections

LB · Chat / text · Objective

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

Rank #86 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.3%
Percentile: 21.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

21.3% percentile inside its fair comparison set

71.3%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 37.8%
Percentile: 18.5%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

18.5% percentile inside its fair comparison set

37.8%Raw benchmark value

Typos

LB · Chat / text · Objective

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

Rank #91 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 62%
Percentile: 16.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

16.8% percentile inside its fair comparison set

62%Raw benchmark value

Coding23 benchmarks38.3%

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 #73 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 27.3%
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

76.2% percentile inside its fair comparison set

27.3%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 #138 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 34.4%
Percentile: 63%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

63% percentile inside its fair comparison set

34.4%Raw 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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #68. Votes: 22687. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,320 - 1,331

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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev. Source rank: #68. Votes: 22687. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,320 - 1,331

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 #55 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev-html. Source rank: #68. Votes: 11943. Organization: anthropic. License: Proprietary.

26% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,305 - 1,323

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 #46 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,328
Percentile: 23.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: webdev-react. Source rank: #58. Votes: 10707. Organization: anthropic. License: Proprietary.

23.7% percentile inside its fair comparison set

1,328Raw benchmark valueCI 1,321 - 1,335

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 #20 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 7.6%
Percentile: 13.6%
Last updated: recent
Eligibility: headline eligible

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

13.6% percentile inside its fair comparison set

7.6%Raw benchmark valueCI 5.5% - 9.6%

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 #82 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41.2%
Percentile: 10%
Last updated: recent
Eligibility: headline eligible

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

10% percentile inside its fair comparison set

41.2%Raw benchmark valueCI 39% - 43.3%

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 #18 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

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

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

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #43 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.6%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

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

22.2% percentile inside its fair comparison set

66.6%Raw benchmark valueCI 62.5% - 70.7%

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 #24 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43.8%
Percentile: 14.8%
Last updated: recent
Eligibility: headline eligible

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

14.8% percentile inside its fair comparison set

43.8%Raw benchmark valueCI 40% - 47.6%

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 #40 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 11.4%
Percentile: 20.4%
Last updated: recent
Eligibility: headline eligible

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

20.4% percentile inside its fair comparison set

11.4%Raw benchmark valueCI 5.3% - 17.5%

Text Arena · Coding

AR · Coding · Human

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

Rank #56 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 82.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: coding. Source rank: #70. Votes: 22112. Organization: anthropic. License: Proprietary.

82.8% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,474 - 1,484

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 #51 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: coding. Source rank: #61. Votes: 22112. Organization: anthropic. License: Proprietary.

84.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,446 - 1,455

IOI

VALS-AI · Coding · Objective

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

Rank #32 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 6.2%
Percentile: 29.5%
Last updated: recent
Eligibility: headline eligible

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

29.5% percentile inside its fair comparison set

6.2%Raw benchmark valueCI 1.2% - 11.1%

Agentic coding

LB · Coding · Objective

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

Rank #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.3%
Percentile: 28.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

28.7% percentile inside its fair comparison set

33.3%Raw benchmark value

Coding

LB · Coding · Objective

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

Rank #63 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.2%
Percentile: 42.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

42.6% percentile inside its fair comparison set

72.2%Raw benchmark value

JavaScript

LB · Coding · Objective

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

Rank #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 30%
Percentile: 38%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

38% percentile inside its fair comparison set

30%Raw benchmark value

TypeScript

LB · Coding · Objective

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

Rank #69 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 25%
Percentile: 37.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

37.4% percentile inside its fair comparison set

25%Raw benchmark value

Python

LB · Coding · Objective

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

Rank #81 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45%
Percentile: 25.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

25.9% percentile inside its fair comparison set

45%Raw benchmark value

Coding generation

LB · Coding · Objective

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

Rank #79 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 70.4%
Percentile: 28.7%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

28.7% percentile inside its fair comparison set

70.4%Raw benchmark value

Coding completion

LB · Coding · Objective

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

Rank #43 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.9%
Percentile: 61.1%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

61.1% percentile inside its fair comparison set

73.9%Raw benchmark value

Terminal-Bench 2.0

TERMINAL-BENCH · Coding · Objective

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

Rank #22 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 29.8%
Percentile: 30%
Last updated: archived
Eligibility: headline eligible

30% percentile inside its fair comparison set

29.8%Raw benchmark value

Reasoning / math / science17 benchmarks27.5%

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 #289 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 4.3%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

22.2% percentile inside its fair comparison set

4.3%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

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

Rank #177 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 64.6%
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

52.9% percentile inside its fair comparison set

64.6%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

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

Rank #137 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%Raw benchmark value

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 #59 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.2%
Percentile: 34.8%
Last updated: recent
Eligibility: headline eligible

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

34.8% percentile inside its fair comparison set

72.2%Raw benchmark valueCI 67.4% - 77.1%

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 #66 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.7%
Percentile: 27%
Last updated: recent
Eligibility: headline eligible

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

27% percentile inside its fair comparison set

78.7%Raw benchmark valueCI 77.8% - 79.6%

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 #102 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 67.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: math. Source rank: #125. Votes: 5407. Organization: anthropic. License: Proprietary.

67.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,389 - 1,406

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 #108 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: math. Source rank: #128. Votes: 5407. Organization: anthropic. License: Proprietary.

65.9% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,383 - 1,400

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #97 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58%
Percentile: 11.1%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

11.1% percentile inside its fair comparison set

58%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 33.9%
Percentile: 7.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

7.4% percentile inside its fair comparison set

33.9%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

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

Rank #80 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 26.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

26.9% percentile inside its fair comparison set

88%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

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

Rank #108 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 4%
Percentile: 0.9%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

0.9% percentile inside its fair comparison set

4%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

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

Rank #98 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.6%
Percentile: 10.2%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

10.2% percentile inside its fair comparison set

68.6%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

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

Rank #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.3%
Percentile: 20.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

20.4% percentile inside its fair comparison set

71.3%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

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

Rank #79 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 27.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

27.8% percentile inside its fair comparison set

50%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

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

Rank #97 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 9.8%
Percentile: 10.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

10.3% percentile inside its fair comparison set

9.8%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58%
Percentile: 7.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

7.4% percentile inside its fair comparison set

58%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 18%
Percentile: 9.3%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

9.3% percentile inside its fair comparison set

18%Raw benchmark value

Professional reasoning32 benchmarks52.6%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #9 · Source label: anthropic/claude-haiku-4-5-20251001

verified runtimevariant direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.3%
Percentile: 27.3%
Last updated: recent
Eligibility: headline eligible

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

27.3% percentile inside its fair comparison set

54.3%Raw benchmark valueCI 51.7% - 56.8%

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #24 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41
Percentile: 11.5%
Last updated: recent
Eligibility: headline eligible

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

11.5% percentile inside its fair comparison set

41Raw benchmark valueCI 39 - 43

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #49 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.2%
Percentile: 46.7%
Last updated: recent
Eligibility: headline eligible

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

46.7% percentile inside its fair comparison set

81.2%Raw benchmark valueCI 80.3% - 82.2%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #23 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31%
Percentile: 12%
Last updated: recent
Eligibility: headline eligible

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

12% percentile inside its fair comparison set

31%Raw benchmark valueCI 29.9% - 32.1%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #70 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.5%
Percentile: 24.2%
Last updated: recent
Eligibility: headline eligible

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

24.2% percentile inside its fair comparison set

67.5%Raw benchmark valueCI 65.7% - 69.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #46 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 32.7%
Percentile: 11.8%
Last updated: recent
Eligibility: headline eligible

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

11.8% percentile inside its fair comparison set

32.7%Raw benchmark valueCI 28.8% - 36.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #9 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.2%
Percentile: 84%
Last updated: recent
Eligibility: headline eligible

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

84% percentile inside its fair comparison set

85.2%Raw benchmark valueCI 81.5% - 89%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #53 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 81.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: expert. Source rank: #69. Votes: 6618. Organization: anthropic. License: Proprietary.

81.1% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,447 - 1,464

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 #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 78%
Last updated: recent
Eligibility: headline eligible

78% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,411 - 1,422

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 #78 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

76.2% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,379 - 1,390

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_legal_and_government. Source rank: #111. Votes: 6567. Organization: anthropic. License: Proprietary.

70.5% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,406 - 1,422

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 #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 74.9%
Last updated: recent
Eligibility: headline eligible

74.9% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,424 - 1,435

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #70 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 77.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_mathematical. Source rank: #85. Votes: 4472. Organization: anthropic. License: Proprietary.

77.6% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,420 - 1,439

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #101 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_medicine_and_healthcare. Source rank: #123. Votes: 5734. Organization: anthropic. License: Proprietary.

66.1% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,411 - 1,429

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 #62 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 81.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_software_and_it_services. Source rank: #78. Votes: 33588. Organization: anthropic. License: Proprietary.

81.2% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,457 - 1,466

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 #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 77.8%
Last updated: recent
Eligibility: headline eligible

77.8% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #46 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 83.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: expert. Source rank: #54. Votes: 6618. Organization: anthropic. License: Proprietary.

83.6% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,435 - 1,451

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 #87 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 73%
Last updated: recent
Eligibility: headline eligible

73% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,390 - 1,401

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 #90 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,363
Percentile: 72.4%
Last updated: recent
Eligibility: headline eligible

72.4% percentile inside its fair comparison set

1,363Raw benchmark valueCI 1,358 - 1,369

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 #100 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_legal_and_government. Source rank: #121. Votes: 6567. Organization: anthropic. License: Proprietary.

66.8% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,388 - 1,404

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 #104 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 68.1%
Last updated: recent
Eligibility: headline eligible

68.1% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,407

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #71 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 77.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_mathematical. Source rank: #84. Votes: 4472. Organization: anthropic. License: Proprietary.

77.3% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,413 - 1,432

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 #111 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 62.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_medicine_and_healthcare. Source rank: #134. Votes: 5734. Organization: anthropic. License: Proprietary.

62.7% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,377 - 1,394

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 #75 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: industry_software_and_it_services. Source rank: #90. Votes: 33588. Organization: anthropic. License: Proprietary.

77.2% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,431 - 1,439

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 #85 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 74.1%
Last updated: recent
Eligibility: headline eligible

74.1% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,379 - 1,389

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #37 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 31.8%
Percentile: 20%
Last updated: recent
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

31.8%Raw benchmark valueCI 25.7% - 38%

Public Benefits Bench v1

VALS-AI · Professional reasoning · Objective

Answering public-benefits questions across the benefits lifecycle.

Rank #12 · Source label: anthropic/claude-haiku-4-5-20251001

verified runtimevariant direct

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.5%
Percentile: 8.3%
Last updated: recent
Eligibility: headline eligible

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

8.3% percentile inside its fair comparison set

49.5%Raw benchmark valueCI 47% - 52.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #88 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.1%
Percentile: 19.4%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

19.4% percentile inside its fair comparison set

45.1%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #93 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.3%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

14.8% percentile inside its fair comparison set

45.3%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #90 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 3%
Percentile: 17.6%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

17.6% percentile inside its fair comparison set

3%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #75 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 38.3%
Percentile: 31.5%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

31.5% percentile inside its fair comparison set

38.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #96 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.1%
Percentile: 14.8%
Last updated: archived
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

14.8% percentile inside its fair comparison set

94.1%Raw benchmark value

Search / tool use1 benchmark46%

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 #168 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 32.5%
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

46% percentile inside its fair comparison set

32.5%Raw benchmark value

Long context2 benchmarks56%

Long Context Reasoning

AA · Long context · Objective

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

Rank #111 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43.7%
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

65.4% percentile inside its fair comparison set

43.7%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 #48 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 60.6%
Percentile: 46.6%
Last updated: recent
Eligibility: headline eligible

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

46.6% percentile inside its fair comparison set

60.6%Raw benchmark valueCI 58.7% - 62.5%

Vision understanding12 benchmarks15.2%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #88 · Source label: Claude 4.5 Haiku (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.1%
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

35.6% percentile inside its fair comparison set

55.1%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #75 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 33%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

33% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,110 - 1,142

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 #68 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,130
Percentile: 5.7%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

5.7% percentile inside its fair comparison set

1,130Raw benchmark valueCI 1,097 - 1,163

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 #76 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 32.1%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

32.1% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,103 - 1,148

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 #67 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,142
Percentile: 4.4%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

4.4% percentile inside its fair comparison set

1,142Raw benchmark valueCI 1,105 - 1,180

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,126
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

2.9% percentile inside its fair comparison set

1,126Raw benchmark valueCI 1,107 - 1,146

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 #78 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,092
Percentile: 30.3%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

30.3% percentile inside its fair comparison set

1,092Raw benchmark valueCI 1,076 - 1,108

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,078
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

2.9% percentile inside its fair comparison set

1,078Raw benchmark valueCI 1,045 - 1,111

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 #81 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,097
Percentile: 27.5%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

27.5% percentile inside its fair comparison set

1,097Raw benchmark valueCI 1,074 - 1,119

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 #68 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,116
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

2.9% percentile inside its fair comparison set

1,116Raw benchmark valueCI 1,079 - 1,154

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 #70 · Source label: claude-3-5-haiku-20241022

backfilledproxy backfilledBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,089
Percentile: 2.9%
Last updated: recent
Eligibility: Fallback benchmark identity is visible for context but excluded from default ranking.

2.9% percentile inside its fair comparison set

1,089Raw benchmark valueCI 1,069 - 1,108

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 #58 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 46.1%
Percentile: 1.7%
Last updated: recent
Eligibility: headline eligible

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

1.7% percentile inside its fair comparison set

46.1%Raw benchmark valueCI 43.7% - 48.4%

Document understanding4 benchmarks23.5%

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 #23 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,417
Percentile: 8.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #27. Votes: 26371. Organization: anthropic. License: Proprietary.

8.3% percentile inside its fair comparison set

1,417Raw benchmark valueCI 1,410 - 1,423

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 #19 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 25%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: overall. Source rank: #22. Votes: 26371. Organization: anthropic. License: Proprietary.

25% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,412 - 1,425

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 #17 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 43
Percentile: 15.8%
Last updated: recent
Eligibility: headline eligible

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

15.8% percentile inside its fair comparison set

43Raw benchmark valueCI 41 - 45

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 #34 · Source label: anthropic/claude-haiku-4-5-20251001-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.2%
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

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

45% percentile inside its fair comparison set

62.2%Raw benchmark valueCI 60.3% - 64%

Multilingual14 benchmarks65.6%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #88 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: chinese. Source rank: #110. Votes: 4491. Organization: anthropic. License: Proprietary.

70.5% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,426 - 1,445

Text Arena · French

AR · Multilingual · Human

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

Rank #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: french. Source rank: #100. Votes: 2195. Organization: anthropic. License: Proprietary.

62.5% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,410 - 1,441

Text Arena · German

AR · Multilingual · Human

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

Rank #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 69.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: german. Source rank: #92. Votes: 1484. Organization: anthropic. License: Proprietary.

69.6% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,383 - 1,417

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #72 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,351
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: japanese. Source rank: #92. Votes: 766. Organization: anthropic. License: Proprietary.

65% percentile inside its fair comparison set

1,351Raw benchmark valueCI 1,327 - 1,375

Text Arena · Korean

AR · Multilingual · Human

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

Rank #73 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,356
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: korean. Source rank: #92. Votes: 1336. Organization: anthropic. License: Proprietary.

65.4% percentile inside its fair comparison set

1,356Raw benchmark valueCI 1,338 - 1,374

Text Arena · Russian

AR · Multilingual · Human

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

Rank #91 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 68.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: russian. Source rank: #112. Votes: 8599. Organization: anthropic. License: Proprietary.

68.9% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,404

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #52 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 76.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: spanish. Source rank: #65. Votes: 2342. Organization: anthropic. License: Proprietary.

76.2% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,411 - 1,440

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 66.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: chinese. Source rank: #121. Votes: 4491. Organization: anthropic. License: Proprietary.

66.8% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,410 - 1,430

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 59.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: french. Source rank: #107. Votes: 2195. Organization: anthropic. License: Proprietary.

59.3% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,391 - 1,421

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #95 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: german. Source rank: #116. Votes: 1484. Organization: anthropic. License: Proprietary.

60.3% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,355 - 1,388

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #82 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,326
Percentile: 60.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: japanese. Source rank: #102. Votes: 766. Organization: anthropic. License: Proprietary.

60.1% percentile inside its fair comparison set

1,326Raw benchmark valueCI 1,303 - 1,350

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #89 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: korean. Source rank: #109. Votes: 1336. Organization: anthropic. License: Proprietary.

57.7% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,316 - 1,352

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 66.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: russian. Source rank: #121. Votes: 8599. Organization: anthropic. License: Proprietary.

66.1% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,369 - 1,383

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #65 · Source label: claude-haiku-4-5-20251001

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 70.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `claude-haiku-4-5-20251001`. Category: spanish. Source rank: #79. Votes: 2342. Organization: anthropic. License: Proprietary.

70.1% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,401 - 1,429