Llama 3.1 8B Instruct logo

Llama 3.1 8B Instruct

Meta Llama

Llama 3.1 8B Instruct is a cutting-edge, multilingual large language model designed for engaging conversations. With an extensive 128K context window, this model excels at complex reasoning and incorporates state-of-the-art tools for enhanced functionality.

Model Specifications

Technical details and capabilities of Llama 3.1 8B Instruct

Core Specifications

8.0B Parameters

Model size and complexity

15000.0B Training Tokens

Amount of data used in training

131.1K / 131.1K

Input / Output tokens

December 30, 2023

Knowledge cutoff date

July 22, 2024

Release date

Capabilities & License

Multimodal Support
Not Supported
Web Hydrated
No
License
Llama 3.1 Community License

Resources

API Reference
https://www.llama.com/
Code Repository
https://github.com/meta-llama/llama-models

Performance Insights

Check out how Llama 3.1 8B Instruct handles various AI tasks through comprehensive benchmark results.

90
68
45
23
0
84.5
GSM-8K (CoT)
84.5
(94%)
83.4
ARC Challenge
83.4
(93%)
82.6
API-Bank
82.6
(92%)
80.4
IFEval
80.4
(89%)
76.1
BFCL
76.1
(85%)
73
MMLU (CoT)
73
(81%)
72.8
MBPP EvalPlus (base)
72.8
(81%)
72.6
HumanEval
72.6
(81%)
69.4
MMLU
69.4
(77%)
68.9
Multilingual MGSM (CoT)
68.9
(77%)
60
CRAG
60
(67%)
59.5
DROP
59.5
(66%)
52.4
Multipl-E MBPP
52.4
(58%)
51.9
MATH (CoT)
51.9
(58%)
50.8
Multipl-E HumanEval
50.8
(56%)
48.3
MMLU-Pro
48.3
(54%)
38.5
Nexus
38.5
(43%)
30.4
GPQA
30.4
(34%)
29.2
HELMET LongQA
29.2
(32%)
28.4
FinanceBench
28.4
(32%)
28.2
Arena Hard
28.2
(31%)
17.7
LongBench
17.7
(20%)
8.2
Gorilla Benchmark API Bench
8.2
(9%)
GSM-8K (CoT)
ARC Challenge
API-Bank
IFEval
BFCL
MMLU (CoT)
MBPP EvalPlus (base)
HumanEval
MMLU
Multilingual MGSM (CoT)
CRAG
DROP
Multipl-E MBPP
MATH (CoT)
Multipl-E HumanEval
MMLU-Pro
Nexus
GPQA
HELMET LongQA
FinanceBench
Arena Hard
LongBench
Gorilla Benchmark API Bench

Model Comparison

See how Llama 3.1 8B Instruct stacks up against other leading models across key performance metrics.

90
72
54
36
18
0
69.4
MMLU - Llama 3.1 8B Instruct
69.4
(77%)
79
MMLU - Claude 3 Sonnet
79
(88%)
83.6
MMLU - Llama 3.1 70B Instruct
83.6
(93%)
84.8
MMLU - Phi-4
84.8
(94%)
86.8
MMLU - Claude 3 Opus
86.8
(96%)
85.9
MMLU - Gemini 1.5 Pro
85.9
(95%)
48.3
MMLU-Pro - Llama 3.1 8B Instruct
48.3
(54%)
56.8
MMLU-Pro - Claude 3 Sonnet
56.8
(63%)
66.4
MMLU-Pro - Llama 3.1 70B Instruct
66.4
(74%)
70.4
MMLU-Pro - Phi-4
70.4
(78%)
68.5
MMLU-Pro - Claude 3 Opus
68.5
(76%)
75.8
MMLU-Pro - Gemini 1.5 Pro
75.8
(84%)
30.4
GPQA - Llama 3.1 8B Instruct
30.4
(34%)
40.4
GPQA - Claude 3 Sonnet
40.4
(45%)
41.7
GPQA - Llama 3.1 70B Instruct
41.7
(46%)
56.1
GPQA - Phi-4
56.1
(62%)
50.4
GPQA - Claude 3 Opus
50.4
(56%)
59.1
GPQA - Gemini 1.5 Pro
59.1
(66%)
72.6
HumanEval - Llama 3.1 8B Instruct
72.6
(81%)
73
HumanEval - Claude 3 Sonnet
73
(81%)
80.5
HumanEval - Llama 3.1 70B Instruct
80.5
(89%)
82.6
HumanEval - Phi-4
82.6
(92%)
84.9
HumanEval - Claude 3 Opus
84.9
(94%)
84.1
HumanEval - Gemini 1.5 Pro
84.1
(93%)
59.5
DROP - Llama 3.1 8B Instruct
59.5
(66%)
78.9
DROP - Claude 3 Sonnet
78.9
(88%)
79.6
DROP - Llama 3.1 70B Instruct
79.6
(88%)
75.5
DROP - Phi-4
75.5
(84%)
83.1
DROP - Claude 3 Opus
83.1
(92%)
74.9
DROP - Gemini 1.5 Pro
74.9
(83%)
MMLU
MMLU-Pro
GPQA
HumanEval
DROP
Llama 3.1 8B Instruct
Claude 3 Sonnet
Llama 3.1 70B Instruct
Phi-4
Claude 3 Opus
Gemini 1.5 Pro

Detailed Benchmarks

Dive deeper into Llama 3.1 8B Instruct's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Coding

HumanEval

Claude 3.5 Sonnet
Claude 3.5 Sonnet
93.7%
Claude 3 Haiku
Claude 3 Haiku
75.9%
Gemini 1.5 Flash
Gemini 1.5 Flash
74.3%
Grok-1.5
Grok-1.5
74.1%
Claude 3 Sonnet
Claude 3 Sonnet
73.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
72.6%
Pixtral-12B
72.0%
Phi-3.5-MoE-instruct
70.7%
GPT-3.5 Turbo
68.0%
Ministral 8B Instruct
Ministral 8B Instruct
34.8%
Current model
Other models
Avg (70.9%)

Reasoning

DROP

Nova Micro
79.3%
Claude 3 Sonnet
Claude 3 Sonnet
78.9%
Claude 3 Haiku
Claude 3 Haiku
78.4%
Phi-4
75.5%
Gemini 1.5 Pro
Gemini 1.5 Pro
74.9%
Olmo 2 32B
Olmo 2 32B
74.3%
GPT-3.5 Turbo
70.2%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
59.5%
Current model
Other models
Avg (73.9%)

Knowledge

MMLU

o1
91.8%
Gemma 2 9B
Gemma 2 9B
71.3%
Qwen2 7B Instruct
Qwen2 7B Instruct
70.5%
GPT-3.5 Turbo
69.8%
Jamba 1.5 Mini
69.7%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
69.4%
Pixtral-12B
69.2%
Phi-3.5-mini-instruct
69.0%
Mistral NeMo Instruct
Mistral NeMo Instruct
68.0%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
63.4%
Current model
Other models
Avg (71.2%)

GPQA

o3
87.7%
Llama 3.2 11B Instruct
Llama 3.2 11B Instruct
32.8%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
32.8%
Jamba 1.5 Mini
32.3%
GPT-3.5 Turbo
30.8%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
30.4%
Phi-3.5-mini-instruct
30.4%
Gemini 1.0 Pro
Gemini 1.0 Pro
27.9%
Qwen2 7B Instruct
Qwen2 7B Instruct
25.3%
Current model
Other models
Avg (36.7%)

Non categorized

MMLU (CoT)

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
88.6%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
86.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
73.0%
Current model
Other models
Avg (82.5%)

MMLU-Pro

DeepSeek-R1
DeepSeek-R1
84.0%
Phi-3.5-MoE-instruct
54.3%
Jamba 1.5 Large
53.5%
Grok-1.5
Grok-1.5
51.0%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
50.4%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
48.3%
Phi-3.5-mini-instruct
47.4%
Qwen2 7B Instruct
Qwen2 7B Instruct
44.1%
Jamba 1.5 Mini
42.5%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
40.1%
Current model
Other models
Avg (51.6%)

IFEval

Claude 3.7 Sonnet
Claude 3.7 Sonnet
93.2%
GPT-4o
84.0%
QwQ 32B
QwQ 32B
83.9%
DeepSeek-R1
DeepSeek-R1
83.3%
Mistral Small 3
Mistral Small 3
82.9%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
80.4%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
77.4%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
71.2%
Phi-4
63.0%
Pixtral-12B
61.3%
Current model
Other models
Avg (78.1%)

ARC Challenge

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
96.9%
Phi-3.5-MoE-instruct
91.0%
Claude 3 Haiku
Claude 3 Haiku
89.2%
Jamba 1.5 Mini
85.7%
Phi-3.5-mini-instruct
84.6%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
83.4%
Ministral 8B Instruct
Ministral 8B Instruct
71.9%
Command R+
71.0%
Llama 3.1 Nemotron 70B Instruct
Llama 3.1 Nemotron 70B Instruct
69.2%
Qwen2 72B Instruct
Qwen2 72B Instruct
68.9%
Current model
Other models
Avg (81.2%)

Multipl-E HumanEval

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
75.2%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
65.5%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
50.8%
Current model
Other models
Avg (63.8%)

Multipl-E MBPP

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
65.7%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
62.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
52.4%
Current model
Other models
Avg (60.0%)

GSM-8K (CoT)

Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
95.1%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
84.5%
Current model
Other models
Avg (89.8%)

MATH (CoT)

Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
68.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
51.9%
Current model
Other models
Avg (60.0%)

API-Bank

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
92.0%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
90.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
82.6%
Current model
Other models
Avg (88.2%)

BFCL

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
88.5%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
84.8%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
76.1%
GPT-4o
74.0%
Nova Pro
68.4%
Nova Lite
66.6%
QwQ 32B
QwQ 32B
66.4%
Command A
Command A
65.0%
Nova Micro
56.2%
Current model
Other models
Avg (71.8%)

Gorilla Benchmark API Bench

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
35.3%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
29.7%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
8.2%
Current model
Other models
Avg (24.4%)

Nexus

Llama 3.1 405B Instruct
Llama 3.1 405B Instruct
58.7%
Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
56.7%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
38.5%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
34.3%
Current model
Other models
Avg (47.0%)

Multilingual MGSM (CoT)

Llama 3.1 70B Instruct
Llama 3.1 70B Instruct
86.9%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
68.9%
Current model
Other models
Avg (77.9%)

Arena Hard

Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
65.8%
Jamba 1.5 Large
65.4%
Jamba 1.6 Mini
Jamba 1.6 Mini
51.2%
Jamba 1.5 Mini
46.1%
Phi-3.5-MoE-instruct
37.9%
Phi-3.5-mini-instruct
37.0%
Command R+
33.1%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
28.2%
Current model
Other models
Avg (45.6%)

CRAG

Jamba 1.6 Large
Jamba 1.6 Large
78.2%
Jamba 1.6 Mini
Jamba 1.6 Mini
76.2%
Mistral Large 2
Mistral Large 2
67.0%
Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
61.7%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
60.0%
Ministral 8B Instruct
Ministral 8B Instruct
52.0%
Nova Pro
50.3%
Command R+
49.4%
Nova Micro
43.1%
Current model
Other models
Avg (59.8%)

FinanceBench

Jamba 1.6 Large
Jamba 1.6 Large
64.5%
Jamba 1.6 Mini
Jamba 1.6 Mini
45.4%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
28.4%
Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
20.0%
Ministral 8B Instruct
Ministral 8B Instruct
19.2%
Command R+
13.3%
Current model
Other models
Avg (31.8%)

HELMET LongQA

Jamba 1.6 Large
Jamba 1.6 Large
56.7%
Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
52.8%
Jamba 1.6 Mini
Jamba 1.6 Mini
46.9%
Command R+
44.8%
Ministral 8B Instruct
Ministral 8B Instruct
33.0%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
29.2%
Mistral Large 2
Mistral Large 2
26.7%
Current model
Other models
Avg (41.4%)

LongBench

Jamba 1.6 Large
Jamba 1.6 Large
38.8%
Mistral Large 2
Mistral Large 2
34.4%
Jamba 1.6 Mini
Jamba 1.6 Mini
32.0%
Llama 3.3 70B Instruct
Llama 3.3 70B Instruct
21.7%
Command R+
18.9%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
17.7%
Ministral 8B Instruct
Ministral 8B Instruct
17.5%
Current model
Other models
Avg (25.9%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Llama 3.1 8B Instruct. 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

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models