Intelligence index
Outperforms 76% of compared models
MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.
Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.
- Input / output price
- $0.3/$1.2per 1M tokens
- Context
- 1.0M
- Released
- 2026-05-31
Pricing
Artificial Analysis
Explore rankingsCoding index
Outperforms 67% of compared models
Agentic index
Outperforms 70% of compared models
Design Arena
Elo scores and win rates across design and agent tasks.
Category performance
1,000-1,500 EloModel Arena
Asciiart
1158Elo
Win rate 46.3%
Website
1256Elo
Win rate 51.6%
Code Categories
1245Elo
Win rate 50.6%
Data Visualization
1235Elo
Win rate 51.2%
UI Component
1240Elo
Win rate 50.5%
SVG
1158Elo
Win rate 44.8%
3D
1205Elo
Win rate 50.1%
Game Development
1210Elo
Win rate 45.6%
Agent Arena
Htmlslides
1076Elo
Win rate 46.7%
Blender3d
1094Elo
Win rate 42.6%
Python-pptxslides
1159Elo
Win rate 47%
Agenticgamedev
1125Elo
Win rate 44.1%
Fullstack
1197Elo
Win rate 47.2%
Spreadsheet
1065Elo
Win rate 46.1%
Androidnative
1162Elo
Win rate 44.8%
Webapps
1201Elo
Win rate 47.1%
Mobile Apps
1167Elo
Win rate 45.7%
Related Models
MiniMax M3.1 Flash
minimaxMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.
- Context
- 1.0M
- Max output
- 524.3K
- Released
- 2026-10-19
- Input
- $0.15/M
- Output
- $0.6/M
- Cache read
- $0.015/M
MiniMax M2.5
minimaxMiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
- Context
- 205K
- Max output
- 131.1K
- Released
- 2026-02-12
- Input
- $0.3/M
- Output
- $1.2/M
- Cache read
- $0.03/M
MiniMax M2.7
minimaxMiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.
- Context
- 205K
- Max output
- 131.1K
- Released
- 2026-03-18
- Input
- $0.3/M
- Output
- $1.2/M
- Cache read
- $0.06/M