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.
發布日期
2025-11-18
參數規模
—
上下文長度
—
支援模態
audio, image, text, video
能力雷達圖
100
general
100
coding
70
reasoning
77
science估算
70
agents
80
multimodal
缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
85.4%自報
Factuality
SimpleQA
72.1%自報
Language
MMMLU
91.8%自報
Long Context
MRCR v2 (8-needle)
26.3%自報
Math
AIME 2025
100.0%自報
LiveBench
73.4%
MathArena Apex
23.4%自報
Multimodal
VideoMMMU
87.6%自報
Reasoning
Vending-Bench 2
547816.0%自報
LiveCodeBench Pro
2439.00 / 3000自報
Global PIQA
93.4%自報
GPQANYU + Cohere + Anthropic (2023)
91.9%自報
CharXiv-R
81.4%自報
SWE-Bench Verified
76.2%自報
FACTS Grounding
70.5%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)
54.2%自報
Humanity's Last Exam
45.8%自報
ARC-AGI v2
31.1%自報
Vision
MMMU-Pro
81.0%自報
ScreenSpot Pro
72.7%自報
OmniDocBench 1.5
11.5%自報
AA 評測指數
(Artificial Analysis)暫無 AA 評測資料
LLM Stats 分類評分
(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
定價
輸入價格$2 / 1M tokens
輸出價格$12 / 1M tokens
速度
暫無速度資料
供應商價格排行
供應商價格排行
1 個供應商
供應商輸入輸出
1Google主要
$2
$12
比較該模型在不同 API 供應商之間的定價。