Mercury 3
InceptionProprietary
描述
Mercury 3 is Inception's flagship diffusion-based LLM (dLLM), released 2026-10-19 and described as the most capable diffusion LLM released to date. Inception says it is more than 40x larger in total parameters than Mercury 1 and runs at about 1,068 output tokens per second on NVIDIA GPUs while matching or beating speed-optimized models such as GPT-6 Luna and Claude Haiku 5.5. It has a 1M-token context window, up to 131,072 output tokens, tunable reasoning effort (instant, low, medium, high), tool calling, and structured outputs. Text in, text out. Available on the Inception API, OpenRouter, Vercel AI Gateway, and Baseten.
發布日期
2026-10-19
參數規模
—
上下文長度
1.0M
支援模態
text
能力雷達圖
100
general
50
coding
100
reasoning
77
science估算
30
agents
0
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
| 領域 | #排名 | 分數 | 來源 |
|---|---|---|---|
| 智慧體能力模型榜 | 26 | 59.0 | LS |
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Agents
SWE-Atlas
51.1%自報
Tau3 Banking
30.2%自報
Chat
Multi-Challenge
60.4%自報
Code
DeepSWE 1.0
46.3%自報
General
GDPval-AA
1237.20 / 3000自報
Instruction Following
IFBench
76.8%自報
Long Context
MRCR v2
75.5%自報
Reasoning
GPQANYU + Cohere + Anthropic (2023)
89.2%自報
AA-LCR
77.7%自報
Science
OmniScience
46.4%自報
Search
DeepSearchQA
71.3%自報
BrowseComp-Plus
55.2%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))Legal100
Finance100
Agents100
Reasoning100
General100
Physics90
Biology90
Chemistry90
Instruction Following80
Long Context80
Search70
Chat60
Communication60
Knowledge50
Science50
Code50
Tool Calling30
定價
輸入價格$0 / 1M tokens
輸出價格$0 / 1M tokens
混合價格(3:1)$0 / 1M tokens
快取讀取價格$0.01 / 1M tokens
速度
暫無速度資料
供應商價格排行
供應商價格排行
6 個供應商
最便宜: Inception最貴: Kilo Gateway
供應商輸入輸出
1Inception主要
$0
$0
2NanoGPT
$0.1
$0.35
3OpenRouter
$0.1
$0.35
4Venice AI
$0.1
$0.35
5Vercel AI Gateway
$0.1
$0.35
6Kilo Gateway
$0.2
$0.7
比較該模型在不同 API 供應商之間的定價。