Models

Release date

Models

Llama 4 Maverick

Release Date: 4/5/2025

Benchmarked by Vals Logo

Llama 4 Maverick SOTA 128-expert MoE powerhouse for multilingual image/text understanding.

Avg. Accuracy

49.96%

Latency

19.94s

Cost (In/Out)

0.22 / 0.88

Context Window

1M

Max Output Tokens

16k

Input Modality

Benchmarks

Accuracy

Rankings

0.0%

29/ 29

0.0%

29/ 29

Vals Multimodal Index

0.0%

18/ 18

0.0%

18/ 18

0.0%

57/ 57

0.0%

57/ 57

0.0%

80/ 80

0.0%

80/ 80

0.0%

55/ 55

0.0%

55/ 55

0.0%

56/ 56

0.0%

56/ 56

0.0%

36/ 36

0.0%

36/ 36

0.0%

86/ 86

0.0%

86/ 86

0.0%

76/ 76

0.0%

76/ 76

0.0%

77/ 77

0.0%

77/ 77

0.0%

84/ 84

0.0%

84/ 84

0.0%

100/ 100

0.0%

100/ 100

0.0%

59/ 59

0.0%

59/ 59

0.0%

84/ 84

0.0%

84/ 84

0.0%

73/ 73

0.0%

73/ 73

0.0%

78/ 78

0.0%

78/ 78

0.0%

55/ 55

0.0%

55/ 55

0.0%

43/ 43

0.0%

43/ 43

0.0%

45/ 45

0.0%

45/ 45

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Join our mailing list to receive benchmark updates

Model benchmarks are seriously lacking. With Vals AI, we report how language models perform on the industry-specific tasks where they will be used.

By subscribing, I agree to Vals' Privacy Policy.