Released date

Model

Last Updated 3/6/2025

Jamba 1.6 Large

The most powerful and efficient long context model

Released Date: 3/6/2025

Avg. Accuracy:

49.9%

Latency:

11.42s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

50.7%

( 29 / 39 )

50.7%

29 / 39

CaseLaw

71.8%

( 49 / 62 )

71.8%

49 / 62

ContractLaw

61.2%

( 59 / 69 )

61.2%

59 / 69

TaxEval

65.3%

( 36 / 49 )

65.3%

36 / 49

Math500

54.8%

( 43 / 45 )

54.8%

43 / 45

AIME

0.4%

( 38 / 39 )

0.4%

38 / 39

MGSM

75.0%

( 40 / 43 )

75.0%

40 / 43

LegalBench

74.1%

( 38 / 67 )

74.1%

38 / 67

MedQA

50.7%

( 46 / 47 )

50.7%

46 / 47

GPQA

24.2%

( 39 / 40 )

24.2%

39 / 40

MMLU Pro

49.3%

( 38 / 40 )

49.3%

38 / 40

LiveCodeBench

21.5%

( 38 / 41 )

21.5%

38 / 41

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.00 / M Tokens

Output Cost

$8.00 / M Tokens

Input Cost (per char)

$0.58 / M chars

Output Cost (per char)

$2.58 / M chars

Performance by Benchmark

Cost Analysis

Join our mailing list to receive benchmark updates on