Provider logo

MiniMax M1

MiniMax-M1
Provider logo

MiniMax M1

MiniMax-M1

MiniMax-M1 is a hybrid MoE reasoning model with 40K thinking budget. World's first open-weight, large-scale hybrid-attention model with lightning attention for efficient test-time compute scaling. Excels at complex tasks requiring extensive reasoning.

Added Jan 8, 2025

Context Window

1.0M

Max Output

131.1K

Input Price (Auto)

$0.14/1M

Output Price (Auto)

$1.33/1M

Cache Read (Auto)

$0.070/1M

Benchmarks

Performance metrics and benchmarks

Sourced from LMArena.

Arena Score

1363.3

Overall Rank

#180 / 389

Votes

35,269

Confidence Interval

1359.0 - 1367.5

Category Scores

Coding

#175 / 384

6,507 votes

1415.7

Math

#171 / 374

1,783 votes

1370.7

Longer Query

#186 / 367

7,101 votes

1362.5

Creative Writing

#191 / 387

4,561 votes

1317.6

Instruction Following

#186 / 389

8,788 votes

1345.3

Hard Prompts

#179 / 389

15,925 votes

1380.1

Additional Categories
22

French

#134 / 271

426 votes

1410.6

German

#151 / 293

832 votes

1359.2

Polish

#159 / 215

3,498 votes

1353.1

Industry Mathematical

#166 / 368

1,778 votes

1378.0

Industry Medicine And Healthcare

#170 / 357

2,129 votes

1392.7

Spanish

#171 / 272

725 votes

1354.4

English

#176 / 389

16,872 votes

1383.9

Industry Life And Physical And Social Science

#178 / 387

5,909 votes

1381.2

Korean

#178 / 264

639 votes

1274.2

Industry Entertainment And Sports And Media

#179 / 387

6,322 votes

1325.4

Industry Software And It Services

#179 / 389

11,715 votes

1402.0

Chinese

#180 / 360

1,843 votes

1383.4

Exclude Ties

#180 / 389

24,829 votes

1328.5

Multi Turn

#183 / 387

5,728 votes

1356.1

Hard Prompts English

#184 / 388

8,188 votes

1393.2

Expert

#185 / 339

1,646 votes

1363.3

Russian

#185 / 352

1,931 votes

1348.6

Non English

#187 / 389

18,388 votes

1338.7

Industry Business And Management And Financial Operations

#188 / 382

6,149 votes

1351.7

Industry Legal And Government

#189 / 361

2,449 votes

1365.9

Industry Writing And Literature And Language

#193 / 388

7,841 votes

1331.2

Japanese

#193 / 256

777 votes

1225.6

Published 2026-08-12 · Matched as minimax-m1

LMArena Dataset

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare MiniMax M1 with similar models from the same provider or model family.

MiniMax M3

minimax/minimax-m3

MiniMax M3 is the non-thinking route for MiniMax's open-weights frontier model, built for coding, agent workflows, tool use, and multimodal understanding from step zero. It keeps native thinking disabled for faster direct answers. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax M3 Thinking

minimax/minimax-m3:thinking

MiniMax M3 Thinking is the adaptive-thinking version of MiniMax's open-weights frontier model for coding, agent workflows, tool use, long-context tasks, and native multimodal understanding. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax Latest

minimax/minimax-latest

Compatibility alias that routes to the newest MiniMax text model. Currently routes to MiniMax M3 (adaptive thinking).

MiniMax M2.7

minimax/minimax-m2.7

MiniMax M2.7 is the first model deeply involved in iterating on its own training. It excels in real-world software engineering (SWE-Pro 56.22%), end-to-end project delivery (VIBE-Pro 55.6%), and complex office workflows with strong tool-use compliance and agentic capabilities.

MiniMax M2.7 Turbo

minimax/minimax-m2.7-turbo

MiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.

MiniMax M2.5

minimax/minimax-m2.5

MiniMax M2.5 is a productivity-focused flagship model that builds on M2.1 with stronger coding and real-world office workflow performance (Word, Excel, PowerPoint), plus better tool-use planning and token efficiency.