Gemini 1.5 Flash-8B
GoogleGeminiProprietary
描述
A multimodal model capable of processing audio, images, video, and text with high efficiency. Features JSON mode, function calling, code execution, and system instructions support. Optimized for fast inference with 8B parameters.
發布日期
2024-10-03
參數規模
8.0B
上下文長度
—
支援模態
image, text
能力雷達圖
21
general
22
coding
30
reasoning
26
science
28
agents
80
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Language
FLEURS
86.4%自報
WMT23
72.6%自報
MMLU-Pro
58.7%自報
Long Context
MRCR
54.7%自報
Math
MATH
58.7%自報
MathVista
54.7%自報
HiddenMath
32.8%自報
Multimodal
Video-MME
66.2%自報
MMMU
53.7%自報
Vibe-Eval
40.9%自報
Reasoning
Natural2Code
75.5%自報
GPQANYU + Cohere + Anthropic (2023)
38.4%自報
Safety
XSTest
92.6%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))68.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))56.9
Gpqa(NYU + Cohere + Anthropic (2023))35.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))21.7
Intelligence Index(Artificial Analysis)6.2
Hle(Center for AI Safety + Scale AI (2025))4.7
Aime(MAA (Mathematical Association of America))3.3
LLM Stats 分類評分
(LLM Stats (zeroeval))Safety90
Speech To Text90
Language70
Legal60
Finance60
General60
Healthcare60
Long Context50
Math50
Multimodal50
Reasoning50
Vision50
Physics40
Biology40
Chemistry40
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