跳轉到主要內容

MiniMax-M2.5

MiniMaxMiniMaxOpen WeightMIT · Commercial OK

描述

MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.

發布日期
2026-02-12
參數規模
230.0B
上下文長度
197K
支援模態
image, text

能力雷達圖

37
general
38
coding
85
reasoning
57
science估算
70
agents
60
multimodal

Science 在缺少專門科學評測時使用推理能力代理估算。

排行榜排名

領域#排名分數來源
智能体与工具27
65.0
LS
代码能力榜68
68.0
AA
通用能力榜46
79.0
AA
科学能力71
67.0
AA

基準測試分數 (LLM Stats)

Agents

BrowseComp76.3%自報
MEWC74.4%自報
SWE-Bench Pro55.4%自報
VIBE-Pro54.2%自報

Code

SWE-Bench Verified80.2%自報
Multi-SWE-Bench51.3%自報

Finance

GDPval-MM59.0%自報

General

BFCL_v3_MultiTurn76.8%自報

AA 評測指數

Intelligence Index
41.9
Coding Index
37.4
Tau2
1.0
Gpqa
0.8
Ifbench
0.7
Lcr
0.7
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.2

LLM Stats 分類評分

Frontend Development
80
Search
80
Agents
70
Code
60
Finance
60
General
60
Multimodal
60
Reasoning
60

定價

輸入價格$0.3 / 1M tokens
輸出價格$1.2 / 1M tokens
混合價格(3:1)$0.525 / 1M tokens

速度

Tokens/秒84.0 tokens/s
首Token延遲1.44s
首回答延遲25.25s

可用提供商

(LS 內部計價單位)
提供商輸入價格輸出價格
MiniMax300K1.2M

外部連結