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
100
general
100
coding
70
reasoning
77
science估算
70
agents
80
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
85.4%自报
Factuality
SimpleQA
72.1%自报
Language
MMMLU
91.8%自报
Long Context
MRCR v2 (8-needle)
26.3%自报
Math
AIME 2025
100.0%自报
LiveBench
73.4%
MathArena Apex
23.4%自报
Multimodal
VideoMMMU
87.6%自报
Reasoning
Vending-Bench 2
547816.0%自报
LiveCodeBench Pro
2439.00 / 3000自报
Global PIQA
93.4%自报
GPQANYU + Cohere + Anthropic (2023)
91.9%自报
CharXiv-R
81.4%自报
SWE-Bench Verified
76.2%自报
FACTS Grounding
70.5%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
54.2%自报
Humanity's Last Exam
45.8%自报
ARC-AGI v2
31.1%自报
Vision
MMMU-Pro
81.0%自报
ScreenSpot Pro
72.7%自报
OmniDocBench 1.5
11.5%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Agents100
Code100
Reasoning100
General100
Language90
Physics90
Healthcare90
Biology90
Chemistry90
Frontend Development80
Math70
Multimodal70
Factuality70
Grounding70
Tool Calling70
Vision60
Spatial Reasoning50
Long Context30
Structured Output10
定价
输入价格$2 / 1M tokens
输出价格$12 / 1M tokens
速度
暂无速度数据
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。