MiMo-V2-Pro

XiaomiProprietary

描述

MiMo-V2-Pro is Xiaomi's flagship foundation model built for real-world agentic workloads. A Mixture-of-Experts model with over 1T total parameters and 42B active, roughly 3x larger than MiMo-V2-Flash. Inherits the Hybrid Attention mechanism with a 7:1 ratio and supports up to 1M-token context. Optimized for coding and agent tasks through post-training scaling across diverse agent scenarios, with native support for complex tool calling and multi-step reasoning.

發布日期

2026-03-18

參數規模

1.0T

上下文長度

1.0M

支援模態

text

能力雷達圖

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
智慧體能力模型榜	99	39.0	LS
程式碼能力榜	103	71.0	AA
通用能力榜	60	77.0	AA
科學能力	82	72.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

DeepSearchQA

86.7%自報

PinchBench

81.0%自報

Claw-Eval

61.5%自報

Terminal-Bench 2.0Stanford × Laude Institute (2026)

57.1%自報

Code

SWE-Bench Verified

78.0%自報

SWE-bench Multilingual

71.7%自報

Communication

Tau2 Telecom

96.8%自報

AA 評測指數

(Artificial Analysis)

Intelligence Index(Artificial Analysis)

41.4

Tau2(Sierra + U Toronto + Vector Institute (2025))

1.0

Gpqa(NYU + Cohere + Anthropic (2023))

0.9

Ifbench(Google Research (2023))

0.7

Lcr(Artificial Analysis)

0.7

Scicode(UIUC + Argonne National Lab (2024))

0.4

Terminalbench Hard(Stanford × Laude Institute (2026))

0.4

Hle(Center for AI Safety + Scale AI (2025))

0.3

LLM Stats 分類評分

(LLM Stats (zeroeval))

Communication

100

Reasoning

Frontend Development

General

Tool Calling

Agents

Code

定價

輸入價格免費

輸出價格免費

混合價格(3:1)免費

快取讀取價格$0.0036 / 1M tokens

速度

Tokens/秒0.0

首Token延遲0.00s

首回答延遲0.00s

供應商價格排行

3 個供應商

最便宜: Xiaomi最貴: OpenCode Go

供應商輸入輸出

1Xiaomi最便宜

$0.435

$0.87

2Abacus

3OpenCode Go

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM Stats Artificial Analysis