Gemini 1.5 Pro (Sep '24)
GoogleGeminiProprietary
描述
Gemini 1.5 Pro is a mid-size multimodal model optimized for a wide range of reasoning tasks. It can process large amounts of data at once, including 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages of text.
发布日期
2024-09-24
参数规模
—
上下文长度
—
支持模态
image, text
能力雷达图
29
general
27
coding
50
reasoning
38
science
43
agents
80
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
59.1%自报
Code
HumanEvalOpenAI (2021)
84.1%自报
Finance
MMLU
85.9%自报
MMLU-Pro
75.8%自报
General
Natural2Code
85.4%自报
MRCR
82.6%自报
MMMU
65.9%自报
Vibe-Eval
53.9%自报
Healthcare
WMT23
75.1%自报
Language
FLEURS
93.3%自报
BIG-Bench Hard
89.2%自报
Math
GSM8k
90.8%自报
MGSM
87.5%自报
MATH
86.5%自报
DROP
74.9%自报
MathVista
68.1%自报
FunctionalMATH
64.6%自报
PhysicsFinals
63.9%自报
HiddenMath
52.0%自报
AMC_2022_23
46.4%自报
Multimodal
Video-MME
78.6%自报
Reasoning
HellaSwagAI2 (2019)
93.3%自报
Safety
XSTest
98.8%自报
AA 评测指数
(Artificial Analysis)Coding Index(Artificial Analysis)23.6
Intelligence Index(Artificial Analysis)9.9
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.8
Gpqa(NYU + Cohere + Anthropic (2023))0.6
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.3
Scicode(UIUC + Argonne National Lab (2024))0.3
Aime(MAA (Mathematical Association of America))0.2
Hle(Center for AI Safety + Scale AI (2025))0.0
LLM Stats 分类评分
(LLM Stats (zeroeval))Safety100
Speech To Text90
Legal80
Long Context80
Math80
Reasoning80
Language80
Finance80
General80
Healthcare80
Code80
Multimodal70
Vision70
Physics60
Biology60
Chemistry60
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
暂无提供商数据