minimax-m2 - SWE-Bench Verified
SWE-Bench Verified resolved rate 61.0
View sourceMiniMax
MiniMax open-weight reasoning and coding model built for agentic software workflows and production tool use.
Running this yourself: can likely run on your own machine.
OpenRouter
Price record: 2026-11-05. Source: openrouter.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
28.1
Quality Score
---
Arena ELO
Unknown
Parameters
205K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
17 of 22 public signals
Sign in to join the discussion
0
Downloads
0
Likes
Oct 2025
Released
4/5 signals
3/4 signals
5/5 signals
1/4 signals
4/4 signals
Parameters
229B
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: Open weights (unrestricted) · Confident confidence
Gaps we are still tracking
Benchmarks
23
Open Source
1
General
2
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
SWE-Bench Verified resolved rate 61.0
View sourcePrice: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
View sourcePrice: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
View sourcePrice: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
View sourcePrice: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
View sourcePrice: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
Quality: 18.6/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.82% | HumanEval: 0.826%
MiniMax says the M2 family is open-sourced with official self-host guidance for private deployment using runtimes like vLLM and SGLang.
SWE-Bench Verified resolved rate 61.0
MiniMax M2.1:在 Agent 场景下的后训练技术与实践经验 - MiniMax News | MiniMax 模型 语言模型 MiniMax M3.1 Flash MiniMax M3 视频&图片 MiniMax H3 MiniMax H3 Image 语音&音乐 MiniMax Speech 2.8 MiniMax Music 3.0 API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系 加入我们 EN 登录 MiniMax Code API 开放平台 登录 MiniMax Code API 开放平台 模型 语言模型 MiniMax M3.1 Flash NEW MiniMax M3 NEW 视频&图片 MiniMax H3 NEW MiniMax H3 Image NEW 语音&音乐 MiniMax Speech 2.8 NEW MiniMax Music 3.0 NEW API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系
MiniMax 开源新评测集:定义Coding Agent 的生产级标准 - MiniMax News | MiniMax 模型 语言模型 MiniMax M3.1 Flash MiniMax M3 视频&图片 MiniMax H3 MiniMax H3 Image 语音&音乐 MiniMax Speech 2.8 MiniMax Music 3.0 API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系 加入我们 EN 登录 MiniMax Code API 开放平台 登录 MiniMax Code API 开放平台 模型 语言模型 MiniMax M3.1 Flash NEW MiniMax M3 NEW 视频&图片 MiniMax H3 NEW MiniMax H3 Image NEW 语音&音乐 MiniMax Speech 2.8 NEW MiniMax Music 3.0 NEW API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关
MiniMax M2.1: 大幅提升多语言编程,为真实世界复杂任务而生 - MiniMax News | MiniMax 模型 语言模型 MiniMax M3.1 Flash MiniMax M3 视频&图片 MiniMax H3 MiniMax H3 Image 语音&音乐 MiniMax Speech 2.8 MiniMax Music 3.0 API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系 加入我们 EN 登录 MiniMax Code API 开放平台 登录 MiniMax Code API 开放平台 模型 语言模型 MiniMax M3.1 Flash NEW MiniMax M3 NEW 视频&图片 MiniMax H3 NEW MiniMax H3 Image NEW 语音&音乐 MiniMax Speech 2.8 NEW MiniMax Music 3.0 NEW API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系
MiniMax M2 & Agent,大巧若拙 - MiniMax News | MiniMax 模型 语言模型 MiniMax M3.1 Flash MiniMax M3 视频&图片 MiniMax H3 MiniMax H3 Image 语音&音乐 MiniMax Speech 2.8 MiniMax Music 3.0 API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系 加入我们 EN 登录 MiniMax Code API 开放平台 登录 MiniMax Code API 开放平台 模型 语言模型 MiniMax M3.1 Flash NEW MiniMax M3 NEW 视频&图片 MiniMax H3 NEW MiniMax H3 Image NEW 语音&音乐 MiniMax Speech 2.8 NEW MiniMax Music 3.0 NEW API M Plan MiniMax Code 研究 关于我们 公司介绍 新闻 投资者关系 加入我们 En