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:

74.06s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

44.5%

( 2 / 28 )

44.5%

2 / 28

CorpFin

67.3%

( 8 / 39 )

67.3%

8 / 39

CaseLaw

85.3%

( 5 / 63 )

85.3%

5 / 63

ContractLaw

66.0%

( 38 / 69 )

66.0%

38 / 69

TaxEval

75.9%

( 11 / 50 )

75.9%

11 / 50

MortgageTax

62.5%

( 24 / 30 )

62.5%

24 / 30

Math500

93.8%

( 7 / 46 )

93.8%

7 / 46

AIME

76.3%

( 8 / 40 )

76.3%

8 / 40

MGSM

90.6%

( 19 / 44 )

90.6%

19 / 44

LegalBench

81.3%

( 12 / 67 )

81.3%

12 / 67

MedQA

92.7%

( 8 / 48 )

92.7%

8 / 48

GPQA

74.5%

( 8 / 41 )

74.5%

8 / 41

MMLU Pro

83.8%

( 5 / 41 )

83.8%

5 / 41

LiveCodeBench

55.9%

( 12 / 41 )

55.9%

12 / 41

MMMU

75.1%

( 7 / 27 )

75.1%

7 / 27

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