Gemini 1.5 Flash 8B logo

Gemini 1.5 Flash 8B

Google

This highly efficient multimodal model excels at processing various data types, including audio, images, video, and text. Equipped with 8 billion parameters, it's optimized for rapid inference and offers advanced capabilities such as JSON mode, function calling, code execution, and support for system instructions.

Model Specifications

Technical details and capabilities of Gemini 1.5 Flash 8B

Core Specifications

8.0B Parameters

Model size and complexity

1.0M / 8.2K

Input / Output tokens

September 30, 2024

Knowledge cutoff date

March 14, 2024

Release date

Capabilities & License

Multimodal Support
Supported
Web Hydrated
No
License
Proprietary

Resources

API Reference
https://ai.google.dev/docs/gemini_1.5_flash
Playground
https://ai.google.dev/studio
Code Repository
https://github.com/google/generative-ai

Performance Insights

Check out how Gemini 1.5 Flash 8B handles various AI tasks through comprehensive benchmark results.

100
75
50
25
0
92.6
XSTest
92.6
(93%)
86.4
FLEURS
86.4
(86%)
75.5
Natural2Code
75.5
(76%)
72.6
WMT23
72.6
(73%)
66.2
Video-MME
66.2
(66%)
58.7
MMLU-Pro
58.7
(59%)
58.7
MATH
58.7
(59%)
54.7
MRCR
54.7
(55%)
54.7
MathVista
54.7
(55%)
53.7
MMMU
53.7
(54%)
40.9
Vibe-Eval
40.9
(41%)
38.4
GPQA
38.4
(38%)
32.8
HiddenMath
32.8
(33%)
XSTest
FLEURS
Natural2Code
WMT23
Video-MME
MMLU-Pro
MATH
MRCR
MathVista
MMMU
Vibe-Eval
GPQA
HiddenMath

Detailed Benchmarks

Dive deeper into Gemini 1.5 Flash 8B's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Non categorized

Natural2Code

Current model
Other models
Avg (83.4%)

HiddenMath

Current model
Other models
Avg (50.2%)

WMT23

Current model
Other models
Avg (73.4%)

MRCR

Current model
Other models
Avg (63.8%)

MMMU

Current model
Other models
Avg (53.3%)

Vibe-Eval

Current model
Other models
Avg (53.9%)

MathVista

Current model
Other models
Avg (52.2%)

FLEURS

Current model
Other models
Avg (34.2%)

Video-MME

Current model
Other models
Avg (73.6%)

XSTest

Current model
Other models
Avg (96.1%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Gemini 1.5 Flash 8B. 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