Mercury 2
InceptionProprietary
描述
Mercury 2 is the fastest reasoning LLM, built on diffusion-based language model (dLLM) architecture. Instead of generating text token-by-token, it refines multiple text blocks simultaneously, achieving over 1,000 tokens per second on Nvidia Blackwell GPUs — 5x faster than leading speed-optimized LLMs. Supports tool usage and JSON output with 128K context window.
发布日期
2026-02-20
参数规模
—
上下文长度
128K
支持模态
text
能力雷达图
23
general
39
coding
77
reasoning
51
science估算
50
agents
0
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)
Biology
GPQA
74.0%自报
SciCode
38.0%自报
Code
LiveCodeBench
67.0%自报
Communication
Tau2 Airline
53.0%自报
General
IFBench
71.0%自报
Math
AIME 2025
91.1%自报
AA 评测指数
Intelligence Index25.3
Gpqa0.8
Tau20.7
Ifbench0.7
Scicode0.4
Lcr0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats 分类评分
Instruction Following70
General70
Math60
Physics60
Reasoning60
Biology60
Chemistry60
Code50
Communication50
Tool Calling50
定价
输入价格$0.25 / 1M tokens
输出价格$0.75 / 1M tokens
混合价格(3:1)$0.375 / 1M tokens
缓存读取价格$0.025 / 1M tokens
速度
Tokens/秒1239.8
首Token延迟3.43s
首回答延迟3.43s
供应商价格排行
供应商价格排行
6 个供应商
最便宜: Inception最贵: Venice AI
供应商输入输出
1Inception最便宜
$0
$0
2NanoGPT
$0.25
$0.75
3OpenRouter
$0.25
$0.75
4Kilo Gateway
$0.25
$0.75
5Vercel AI Gateway
$0.25
$0.75
6Venice AI
$0.3125
$0.9375
比较该模型在不同 API 供应商之间的定价。