Jamba 1.5 Large

Unknown Developer

This cutting-edge AI excels at following instructions by combining the strengths of SSM and Transformer architectures. This hybrid design allows it to process long sequences of information faster and more effectively, resulting in high-quality outputs.

Model Specifications

Technical details and capabilities of Jamba 1.5 Large

Core Specifications

398.0B Parameters

Model size and complexity

256.0K / 256.0K

Input / Output tokens

March 4, 2024

Knowledge cutoff date

August 21, 2024

Release date

Capabilities & License

Multimodal Support

Not Supported

Web Hydrated

License

Jamba Open Model License

Resources

API Reference

https://docs.ai21.com/reference/jamba-15-api-ref

Performance Insights

Check out how Jamba 1.5 Large handles various AI tasks through comprehensive benchmark results.

100

ARC Challenge

(93%)

GSM-8K

(87%)

81.2

MMLU

81.2

(81%)

65.4

Arena Hard

65.4

(65%)

58.3

TruthfulQA

58.3

(58%)

53.5

MMLU-Pro

53.5

(54%)

48.5

Wild Bench

48.5

(49%)

36.9

GPQA

36.9

(37%)

ARC Challenge

GSM-8K

MMLU

Arena Hard

TruthfulQA

MMLU-Pro

Wild Bench

GPQA

Model Comparison

See how Jamba 1.5 Large stacks up against other leading models across key performance metrics.

100

65.4

Arena Hard - Jamba 1.5 Large

65.4

(65%)

46.1

Arena Hard - Jamba 1.5 Mini

46.1

(46%)

37.9

Arena Hard - Phi-3.5-MoE-instruct

37.9

(38%)

Arena Hard - Phi-3.5-mini-instruct

(37%)

28.2

Arena Hard - Llama 3.1 8B Instruct

28.2

(28%)

81.2

MMLU - Jamba 1.5 Large

81.2

(81%)

69.7

MMLU - Jamba 1.5 Mini

69.7

(70%)

78.9

MMLU - Phi-3.5-MoE-instruct

78.9

(79%)

MMLU - Phi-3.5-mini-instruct

(69%)

69.4

MMLU - Llama 3.1 8B Instruct

69.4

(69%)

53.5

MMLU-Pro - Jamba 1.5 Large

53.5

(54%)

42.5

MMLU-Pro - Jamba 1.5 Mini

42.5

(43%)

54.3

MMLU-Pro - Phi-3.5-MoE-instruct

54.3

(54%)

47.4

MMLU-Pro - Phi-3.5-mini-instruct

47.4

(47%)

48.3

MMLU-Pro - Llama 3.1 8B Instruct

48.3

(48%)

36.9

GPQA - Jamba 1.5 Large

36.9

(37%)

32.3

GPQA - Jamba 1.5 Mini

32.3

(32%)

36.8

GPQA - Phi-3.5-MoE-instruct

36.8

(37%)

30.4

GPQA - Phi-3.5-mini-instruct

30.4

(30%)

30.4

GPQA - Llama 3.1 8B Instruct

30.4

(30%)

ARC Challenge - Jamba 1.5 Large

(93%)

85.7

ARC Challenge - Jamba 1.5 Mini

85.7

(86%)

ARC Challenge - Phi-3.5-MoE-instruct

(91%)

84.6

ARC Challenge - Phi-3.5-mini-instruct

84.6

(85%)

83.4

ARC Challenge - Llama 3.1 8B Instruct

83.4

(83%)

Arena Hard

MMLU

MMLU-Pro

GPQA

ARC Challenge

Jamba 1.5 Large

Jamba 1.5 Mini

Phi-3.5-MoE-instruct

Phi-3.5-mini-instruct

Llama 3.1 8B Instruct

Detailed Benchmarks

Dive deeper into Jamba 1.5 Large's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Knowledge

MMLU

91.8%

83.3%

82.3%

82.0%

81.3%

81.2%

Mistral Small 3.1 24B

80.6%

Nova Lite

80.5%

DeepSeek-V2.5

80.4%

Llama 3.2 3B Instruct

63.4%

Current model

Other models

Avg (80.7%)

GPQA

87.7%

40.4%

40.2%

40.0%

38.4%

36.9%

36.8%

36.4%

35.9%

25.3%

Current model

Other models

Avg (41.8%)

Hallucination

TruthfulQA

Phi-3.5-MoE-instruct

77.5%

Phi-3.5-mini-instruct

64.0%

Llama 3.1 Nemotron 70B Instruct

58.6%

58.4%

58.3%

57.8%

54.8%

Qwen2.5-Coder 32B Instruct

54.2%

Mistral NeMo Instruct

50.3%

Current model

Other models

Avg (59.3%)

Non categorized

Arena Hard

Mistral Small 3

87.6%

Jamba 1.6 Large

76.5%

Mistral Large 2

71.5%

Ministral 8B Instruct

70.9%

Llama 3.3 70B Instruct

65.8%

65.4%

51.2%

46.1%

37.9%

Llama 3.1 8B Instruct

28.2%

Current model

Other models

Avg (60.1%)

Wild Bench

Jamba 1.5 Large

48.5%

Jamba 1.5 Mini

42.4%

Current model

Other models

Avg (45.5%)

MMLU-Pro

84.0%

58.7%

56.8%

56.3%

54.3%

53.5%

51.0%

Qwen2.5-Coder 32B Instruct

50.4%

Llama 3.1 8B Instruct

48.3%

Qwen2.5-Coder 7B Instruct

40.1%

Current model

Other models

Avg (55.3%)

ARC Challenge

Llama 3.1 405B Instruct

96.9%

Claude 3 Opus

96.4%

Llama 3.1 70B Instruct

94.8%

93.2%

93.0%

91.0%

89.2%

85.7%

68.9%

Current model

Other models

Avg (89.9%)

GSM-8K

Jamba 1.5 Large

87.0%

Jamba 1.5 Mini

75.8%

Current model

Other models

Avg (81.4%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Jamba 1.5 Large. Compare costs across platforms to find the best pricing for your use case.

OpenAI

Anthropic

Google

Mistral AI

Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Jamba 1.5 Large

Model Specifications

Core Specifications

Capabilities & License

Resources

Performance Insights

Model Comparison

Detailed Benchmarks

Knowledge

MMLU

GPQA

Hallucination

TruthfulQA

Non categorized

Arena Hard

Wild Bench

MMLU-Pro

ARC Challenge

GSM-8K

Providers Pricing Coming Soon

Share your feedback

Stay Ahead with AI Updates