Released date

Model

Last Updated 12/26/2024

fireworks/deepseek-v3

Released Date: 12/26/2024

Avg. Accuracy:

70.4%

Latency:

17.50s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

60.7%

( 6 / 25 )

60.7%

6 / 25

84.5%

( 5 / 44 )

84.5%

5 / 44

68.4%

( 15 / 51 )

68.4%

15 / 51

72.0%

( 13 / 31 )

72.0%

13 / 31

80.4%

( 10 / 27 )

80.4%

10 / 27

27.5%

( 8 / 23 )

27.5%

8 / 23

92.5%

( 2 / 25 )

92.5%

2 / 25

80.1%

( 3 / 49 )

80.1%

3 / 49

80.9%

( 15 / 29 )

80.9%

15 / 29

54.0%

( 10 / 24 )

54.0%

10 / 24

73.8%

( 12 / 24 )

73.8%

12 / 24

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.90 / M Tokens

Output Cost

$0.90 / M Tokens

Input Cost (per char)

$0.22 / M chars

Output Cost (per char)

$0.25 / M chars

Join our mailing list to receive benchmark updates on

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