Benchmark suiteUpdated May 27, 2026

Claude Sonnet 4.5 20250929.

A model-level benchmark profile for Claude Sonnet 4.5 20250929, 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

#15

Document Arena

Best suite

#24

Coding / 68

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 Sonnet 4.5 20250929 is strongest on coding.

78% coverage

Its best composite result is rank #24 in the coding view, with a 68 coding index. The strongest raw Arena signal is Document Arena at rank #15 with 16,693 public votes.

Best current lane

Coding

#24 / 68 coding index

Strongest raw signal

Docs

#15, 1450 score

Commercial posture

$6.56

0.91s first token / 64 tok/s

Coverage gaps

Vision ArenaSearch Arena

Profile completeness

7 of 9 signals matched

78%

Arena categories

3/5

Docs, Text, Code

Commercial match

Live

Claude 4.5 Sonnet (Non-reasoning)

SWE-bench

#12

bash-only

Raw identifier

claude-sonnet-4-5-20250929

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

1,455#35

1452-1458 CI

76,121 votes

May 27, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,386#43

1380-1392 CI

18,386 votes

May 25, 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

1,450#15

1442-1457 CI

16,693 votes

May 12, 2026

Arena public leaderboard dataset

SWE-bench Verified

Software issue resolution

71.4%#12

bash-only

claude-sonnet-4-5-20250929

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

$6.56

USD / 1M tokens

Input price

$3.75

USD / 1M input tokens

Output price

$15.00

USD / 1M output tokens

Latency

0.91s

Median time to first token

Output speed

64 tok/s

Median generation speed

Matched source row

Claude 4.5 Sonnet (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

#4759

value index

blended / 1M tokens$6.56

time to first token0.91s

output speed64 tok/s

Coding

Code Arena, SWE-bench, and output speed

#2468

coding index

Code Arena rank #431,386