跳转到主要内容
AITier

Gemini 3 Pro Preview (Low)

GoogleGeminiProprietary

描述

Gemini 3 Pro is the first model in the new Gemini 3 series. It is best for complex tasks that require broad world knowledge and advanced reasoning across modalities. Gemini 3 Pro uses dynamic thinking by default to reason through prompts, and features a 1 million-token input context window with 64k output tokens.

发布日期
2025-11-18
参数规模
—
上下文长度
—
支持模态
audio, image, text, video

能力雷达图

44
general
86
coding
87
reasoning
70
science
70
agents
80
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜25
57.0
LS
代码能力榜141
76.0
AA
通用能力榜170
58.0
AA
多模态榜35
60.0
LS
科学能力132
69.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench85.4%自报

Factuality

SimpleQA72.1%自报

Language

MMMLU91.8%自报

Long Context

MRCR v2 (8-needle)26.3%自报

Math

AIME 2025100.0%自报
LiveBench73.4%
MathArena Apex23.4%自报

Multimodal

VideoMMMU87.6%自报

Reasoning

Vending-Bench 2547816.0%自报
LiveCodeBench Pro2439.00 / 3000自报
Global PIQA93.4%自报
GPQANYU + Cohere + Anthropic (2023)91.9%自报
CharXiv-R81.4%自报
SWE-Bench Verified76.2%自报
FACTS Grounding70.5%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)54.2%自报
Humanity's Last Exam45.8%自报
ARC-AGI v231.1%自报

Vision

MMMU-Pro81.0%自报
ScreenSpot Pro72.7%自报
OmniDocBench 1.511.5%自报

AA 评测指数

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
89.5
Gpqa(NYU + Cohere + Anthropic (2023))
88.7
Math Index(Artificial Analysis)
86.7
Aime 25(MAA (Mathematical Association of America))
86.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
85.7
Lcr(Artificial Analysis)
74.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
68.1
Ifbench(Google Research (2023))
49.7
Terminalbench Hard(Stanford × Laude Institute (2026))
34.1
Hle(Center for AI Safety + Scale AI (2025))
29.5
Intelligence Index(Artificial Analysis)
22.3

LLM Stats 分类评分

(LLM Stats (zeroeval))
Agents
100
Code
100
Reasoning
100
General
100
Language
90
Physics
90
Healthcare
90
Biology
90
Chemistry
90
Frontend Development
80
Math
70
Multimodal
70
Factuality
70
Grounding
70
Tool Calling
70
Vision
60
Spatial Reasoning
50
Long Context
30
Structured Output
10

定价

输入价格$2 / 1M tokens
输出价格$12 / 1M tokens
混合价格(3:1)$4.5 / 1M tokens

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

供应商价格排行

1 个供应商

供应商输入输出
1Google主要
$2
$12

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM StatsArtificial Analysis