New Finance Agent Benchmark Released

Released date

Model

Last Updated 9/18/2025

mistralai/magistral-small-2509

Magistral Small 1.2 (09/2025)

Small reasoning model with vision support released in September 2025.

Released Date: 9/18/2025

Avg. Accuracy:

61.5%

Latency:

86.26s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

51.1%

( 43 / 55 )

51.1%

43 / 55

59.2%

( 33 / 38 )

59.2%

33 / 38

64.1%

( 60 / 72 )

64.1%

60 / 72

75.6%

( 13 / 44 )

75.6%

13 / 44

80.2%

( 17 / 62 )

80.2%

17 / 62

86.3%

( 53 / 65 )

86.3%

53 / 65

34.1%

( 87 / 87 )

34.1%

87 / 87

82.4%

( 44 / 68 )

82.4%

44 / 68

52.3%

( 46 / 64 )

52.3%

46 / 64

62.1%

( 59 / 62 )

62.1%

59 / 62

65.2%

( 28 / 41 )

65.2%

28 / 41

72.1%

( 14 / 61 )

72.1%

14 / 61

15.0%

( 22 / 23 )

15.0%

22 / 23

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.50 / M Tokens

Output Cost

$1.50 / M Tokens

Join our mailing list to receive benchmark updates on

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