Released date

Model

Last Updated 5/22/2025

anthropic/claude-sonnet-4-20250514-thinking

Claude Sonnet 4 (Thinking)

Anthropic's latest-generation workhorse model, offering a balance of performance and speed.

Released Date: 5/22/2025

Avg. Accuracy:

75.0%

Latency:

74.01s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

44.5%

( 2 / 24 )

44.5%

2 / 24

CorpFin

67.3%

( 8 / 39 )

67.3%

8 / 39

CaseLaw

84.3%

( 12 / 62 )

84.3%

12 / 62

ContractLaw

66.0%

( 39 / 69 )

66.0%

39 / 69

TaxEval

75.9%

( 11 / 49 )

75.9%

11 / 49

MortgageTax

62.5%

( 24 / 29 )

62.5%

24 / 29

Math500

93.8%

( 6 / 45 )

93.8%

6 / 45

AIME

76.3%

( 7 / 39 )

76.3%

7 / 39

MGSM

90.6%

( 18 / 43 )

90.6%

18 / 43

LegalBench

81.3%

( 12 / 67 )

81.3%

12 / 67

MedQA

92.7%

( 8 / 47 )

92.7%

8 / 47

GPQA

74.5%

( 7 / 40 )

74.5%

7 / 40

MMLU Pro

83.8%

( 4 / 40 )

83.8%

4 / 40

LiveCodeBench

55.9%

( 11 / 40 )

55.9%

11 / 40

MMMU

75.1%

( 6 / 26 )

75.1%

6 / 26

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$3.00 / M Tokens

Output Cost

$15.00 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

N/A

Performance by Benchmark

Cost Analysis

Join our mailing list to receive benchmark updates on