Benchmark suiteUpdated May 19, 2026

Claude Haiku 4.5 20251001.

A model-level benchmark profile for Claude Haiku 4.5 20251001, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Anthropic lab page

Lab

Anthropic

Proprietary

Coverage

78%

7 of 9 tracked signals

Best Arena rank

#23

Document Arena

Best suite

#43

Coding / 57

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Claude Haiku 4.5 20251001 is strongest on coding.

78% coverage

Its best composite result is rank #43 in the coding view, with a 57 coding index. The strongest raw Arena signal is Document Arena at rank #23 with 17,855 public votes.

Best current lane

Coding

#43 / 57 coding index

Strongest raw signal

Docs

#23, 1421 score

Commercial posture

$2.19

0.69s first token / 107 tok/s

Coverage gaps

Vision ArenaSearch Arena

Profile completeness

7 of 9 signals matched

78%

Arena categories

3/5

Docs, Code, Text

Commercial match

Live

Claude 4.5 Haiku (Non-reasoning)

SWE-bench

#19

bash-only

Raw identifier

claude-haiku-4-5-20251001

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,410#99

1407-1413 CI

70,948 votes

May 19, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,321#60

1315-1326 CI

19,976 votes

May 19, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

1,421#23

1414-1428 CI

17,855 votes

May 12, 2026

Arena public leaderboard dataset

SWE-bench Verified

Software issue resolution

66.6%#19

bash-only

claude-haiku-4-5-20251001

Feb 17, 2026

SWE-bench Verified

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$2.19

USD / 1M tokens

Input price

$1.25

USD / 1M input tokens

Output price

$5.00

USD / 1M output tokens

Latency

0.69s

Median time to first token

Output speed

107 tok/s

Median generation speed

Matched source row

Claude 4.5 Haiku (Non-reasoning)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#7146

value index

blended / 1M tokens$2.19

time to first token0.69s

output speed107 tok/s

Coding

Code Arena, SWE-bench, and output speed

#4357

coding index

Code Arena rank #601,321