Gemini 3.7 Flash (High)
GoogleGeminiProprietary
描述
Google's most intelligent Flash workhorse yet for coding and agents. Ships ~3 weeks after Gemini 3.6 Flash with gains on debugging/issue resolution, first-pass code accuracy, FrontierCode 1.1 Main (43.6% vs 3.6's 34.4%), and DeepSWE v1.1 (65.3% vs 48.6%). WebDev Arena Elo 1588 vs 1538; GDP.pdf 34.0% vs 22.0%; AutomationBench 30.4% vs 17.0%. Text/image/video/audio/PDF in, text out; 1M context / 65,536 max output. Powers Gemini Spark for Pro/Ultra. Intro pricing is half of original 3.6 Flash ($0.75/$3.75 per 1M input/output tokens) through 2026-12-31; list price $1.50/$7.50 applies starting 2027-01-01.
发布日期
2026-08-13
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
100
general
100
coding
100
reasoning
51
science估算
40
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
AutomationBench
30.4%自报
Agents' Last Exam
26.3%自报
Biology
LABBench2
82.1%自报
BioMysteryBench
43.5%自报
Code
WebDev Arena
1588.00 / 2000自报
DeepSWE 1.1
65.3%自报
General
GDPval-AA
1525.00 / 3000自报
Artificial Analysis
56.0%自报
GDP.pdf
34.0%自报
Healthcare
LifeSci Diamond (2026-11)
1.8%
Knowledge
Harvey LAB-AA
90.7%自报
HLE-Verified
53.6%自报
Long Context
MRCR v2 (8-needle)
97.0%自报
Multimodal
OSWorld 2.0
47.9%自报
Reasoning
CharXiv-R
88.7%自报
Terminal-Bench 2.1
85.8%自报
FrontierCode 1.1
43.6%自报
Terminal-Bench 3.0
14.9%自报
Vision
LVBench
85.4%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))Frontend Development100
Legal100
Finance100
Code100
Reasoning100
General100
Agents100
Long Context90
Knowledge70
Multimodal60
Science60
Biology60
Vision60
Tool Calling40
定价
输入价格$0.75 / 1M tokens
输出价格$3.75 / 1M tokens
混合价格(3:1)$1.5 / 1M tokens
缓存读取价格$0.075 / 1M tokens
速度
暂无速度数据
供应商价格排行
供应商价格排行
5 个供应商
最便宜: Kenari最贵: Neon
供应商输入输出
1Kenari最便宜
$0.3429
$1.71
2Google主要
$0.75
$3.75
3DeepInfra
$0.75
$3.75
4Venice AI
$0.9375
$4.6875
5Neon
$1.5
$7.5
比较该模型在不同 API 供应商之间的定价。