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

1363.9

Overall Rank

#189 / 402

Votes

34,030

Confidence Interval

1359.6 - 1368.2

Category Scores

Coding

#183 / 397

6,333 votes

1416.3

Math

#181 / 384

1,761 votes

1369.6

Longer Query

#196 / 380

6,916 votes

1363.1

Creative Writing

#200 / 400

4,448 votes

1319.2

Instruction Following

#194 / 402

8,545 votes

1346.1

Hard Prompts

#189 / 402

15,490 votes

1380.6

Additional Categories
22

German

#155 / 299

876 votes

1362.7

French

#157 / 281

465 votes

1395.1

Polish

#166 / 222

3,517 votes

1352.5

Spanish

#173 / 283

823 votes

1367.4

Industry Mathematical

#176 / 379

1,732 votes

1378.2

Korean

#177 / 269

659 votes

1283.3

Industry Medicine And Healthcare

#181 / 371

2,081 votes

1391.2

English

#182 / 402

14,819 votes

1384.7

Chinese

#186 / 373

2,340 votes

1386.4

Industry Life And Physical And Social Science

#188 / 400

5,767 votes

1381.9

Industry Entertainment And Sports And Media

#189 / 400

6,177 votes

1325.4

Industry Software And It Services

#189 / 402

11,124 votes

1402.5

Exclude Ties

#190 / 402

23,914 votes

1329.1

Multi Turn

#190 / 400

5,425 votes

1356.9

Hard Prompts English

#191 / 400

6,942 votes

1395.6

Russian

#191 / 366

2,366 votes

1351.3

Non English

#195 / 402

19,202 votes

1340.5

Japanese

#196 / 265

826 votes

1233.5

Expert

#198 / 352

1,586 votes

1362.7

Industry Business And Management And Financial Operations

#200 / 395

5,989 votes

1351.6

Industry Writing And Literature And Language

#201 / 401

7,635 votes

1332.2

Industry Legal And Government

#204 / 375

2,331 votes

1364.1

Published 2026-09-13 · 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.