Gemini 1.5 Flash (Sep '24)

GoogleGeminiProprietary

描述

Gemini 1.5 Flash is a fast and versatile multimodal model for scaling across diverse tasks. It supports audio, images, video, and text input, and produces text output. The model is optimized for generating code, extracting data, editing text, and more, making it ideal for narrow, high-frequency tasks.

發布日期

2024-09-24

參數規模

—

上下文長度

—

支援模態

image, text

能力雷達圖

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
程式碼能力榜	430	30.0	AA
通用能力榜	464	30.0	AA
多模態榜	104	43.0	LS
科學能力	533	23.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

General

MMLU

78.9%自報

Language

FLEURS

90.4%自報

WMT23

74.1%自報

MMLU-Pro

67.3%自報

Long Context

MRCR

71.9%自報

Math

GSM8k

86.2%自報

MGSM

82.6%自報

MATH

77.9%自報

MathVista

65.8%自報

FunctionalMATH

53.6%自報

HiddenMath

47.2%自報

AMC_2022_23

34.8%自報

Multimodal

Video-MME

76.1%自報

MMMU

62.3%自報

Vibe-Eval

48.9%自報

Physics

PhysicsFinals

57.4%自報

Reasoning

HellaSwagAI2 (2019)

86.5%自報

BIG-Bench Hard

85.5%自報

Natural2Code

79.8%自報

HumanEvalOpenAI (2021)

74.3%自報

GPQANYU + Cohere + Anthropic (2023)

51.0%自報

Safety

XSTest

97.0%自報

AA 評測指數

(Artificial Analysis)

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

82.7

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

68.0

Gpqa(NYU + Cohere + Anthropic (2023))

46.3

Livecodebench(UC Berkeley + MIT + Cornell (2024))

27.3

Aime(MAA (Mathematical Association of America))

18.0

Intelligence Index(Artificial Analysis)

7.1

Hle(Center for AI Safety + Scale AI (2025))

3.2

LLM Stats 分類評分

(LLM Stats (zeroeval))

Safety

100

Speech To Text

Language

Legal

Long Context

Math

Reasoning

Finance

General

Healthcare

Code

Multimodal

Vision

Physics

Biology

Chemistry

定價

輸入價格免費

輸出價格免費

混合價格(3:1)免費

速度

Tokens/秒0.0

首Token延遲0.00s

首回答延遲0.00s

供應商價格排行

暫無提供商資料

外部連結

LLM Stats Artificial Analysis