Mistral Small 2503

Released Date: 3/17/2025

Avg. Accuracy:

61.4%

Latency:

6.52s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

53.2%

( 14 / 26 )

CaseLaw

76.7%

( 24 / 45 )

ContractLaw

65.9%

( 31 / 52 )

TaxEval

62.9%

( 25 / 32 )

MortgageTax

75.0%

( 6 / 16 )

Math500

68.4%

( 23 / 28 )

AIME

3.5%

( 22 / 24 )

MGSM

85.4%

( 21 / 26 )

LegalBench

70.9%

( 30 / 50 )

MedQA

68.7%

( 21 / 30 )

GPQA

41.4%

( 19 / 25 )

MMLU Pro

66.0%

( 17 / 25 )

MMMU

60.6%

( 11 / 15 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.07 / M Tokens

Output Cost

$0.30 / M Tokens

Input Cost (per char)

$0.02 / M chars

Output Cost (per char)

$0.08 / M chars

Join our mailing list to receive benchmark updates on

Stay up to date as new benchmarks and models are released.