Gemini 3 Flash Preview (Reasoning)
GoogleGemini
描述
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost. It combines Gemini 3's Pro-grade reasoning with Flash-level latency, efficiency and cost. Features a 1 million-token input context window and is optimized for agentic workflows, coding, and complex analysis.
发布日期
2025-12-17
参数规模
—
上下文长度
1.0M
支持模态
audio, image, pdf, text, video
能力雷达图
53
general
82
coding
96
reasoning
65
science估算
60
agents
80
multimodal
Science 在缺少专门科学评测时使用推理能力代理估算。
排行榜排名
基准测试分数 (LLM Stats)
Agents
Vending-Bench 2
363500.0%自报
t2-bench
90.2%自报
MCP Atlas
57.4%自报
Toolathlon
49.4%自报
Terminal-Bench 2.0
47.6%自报
Finance Agent v2
42.5%自报
Legal Agent Benchmark
0.0%自报
Biology
GPQA
90.4%自报
Code
LiveCodeBench Pro
2316.00 / 3000自报
SWE-Bench Verified
78.0%自报
Factuality
SimpleQA
68.7%自报
FACTS Grounding
61.9%自报
General
Global PIQA
92.8%自报
MMMLU
91.8%自报
MMMU-Pro
81.2%自报
LiveBench
72.4%自报
MRCR v2 (8-needle)
22.1%自报
Grounding
ScreenSpot Pro
69.1%自报
Healthcare
VideoMMMU
86.9%自报
Math
AIME 2025
99.7%自报
Humanity's Last Exam
43.5%自报
Multimodal
CharXiv-R
80.3%自报
OmniDocBench 1.5
12.1%自报
Reasoning
ARC-AGI v2
33.6%自报
AA 评测指数
Math Index97.0
Intelligence Index37.8
Aime 251.0
Livecodebench0.9
Gpqa0.9
Mmlu Pro0.9
Tau20.8
Ifbench0.8
Lcr0.7
Scicode0.5
Terminalbench Hard0.4
Hle0.3
Tau Banking0.2
LLM Stats 分类评分
Code100
Agents100
General100
Reasoning100
Language90
Physics90
Biology90
Chemistry90
Math80
Frontend Development80
Multimodal70
Factuality70
Grounding70
Tool Calling60
Vision60
Spatial Reasoning50
Healthcare50
Finance40
Long Context20
Structured Output10
Legal0
定价
输入价格$0.5 / 1M tokens
输出价格$3 / 1M tokens
混合价格(3:1)$1.125 / 1M tokens
缓存读取价格$0.05 / 1M tokens
速度
Tokens/秒230.5
首Token延迟5.84s
首回答延迟5.84s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: Google最贵: NanoGPT
供应商输入输出
1Google主要
$0.5
$3
2NanoGPT
$0.5
$3
比较该模型在不同 API 供应商之间的定价。