The LLM benchmark aggregator.

MiniMax M2.1

MiniMax · 229B · open weights

Strongest in Academic knowledge (#34 of 123), weakest in Human preference (#139 of 342). Above par in 8 of 14 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 4.6 and Claude Fable 5 and ahead of MiniMax M2.7 and Claude 3.5 Sonnet.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Knowledge56.1−7.4#37/1381/2

Academic knowledge57.3−6.6#34/1231/1

Coding50.4−18.7#72/1651/5

Agentic coding50.5−18.2#70/1571/4

Reasoning49.1−17.8#93/1782/4

Mathematics53.1−12.6#65/1401/2

Science51.7−11.8#71/1221/1

Reasoning43−26.1#94/1401/3

Professional48.3−13.3#99/1681/1

Medical49.2−17.6#85/1401/1

Finance48.6−14.3#97/1511/1

Legal46.4−20.7#98/1511/1

Human preference55.6−11.9#139/3421/1

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for MiniMax M2.1, left for the other.

Jamba 1.6 Miniwon 9 · lost 0

Jamba 1.6 Largewon 9 · lost 0

Mistral Small 3.1won 9 · lost 0

Laguna XS.2won 10 · lost 0

Laguna M.1won 10 · lost 0

Command R Pluswon 10 · lost 0

Mistral Largewon 10 · lost 0

Gemini 1.5 Flashwon 10 · lost 0

Mistral Smallwon 10 · lost 0

Llama 4 Scout Instructwon 12 · lost 0

Claude 3.5 Haikuwon 12 · lost 0

Gemini 1.5 Prowon 12 · lost 0

GPT-4o Miniwon 13 · lost 0

GPT-4.1 Nanowon 14 · lost 0

Llama 4 Maverick Instructwon 13 · lost 1

Gemini 2.0 Flashwon 13 · lost 1

Command Awon 12 · lost 1

Gemini 2.5 Flash Litewon 10 · lost 1

Mistral Medium 3.5won 11 · lost 2

GPT-5 Nanowon 10 · lost 2

Grok 2won 9 · lost 2

Ling 3.0 Flashwon 8 · lost 2

GPT-4owon 11 · lost 3

GPT OSS 120Bwon 11 · lost 3

Magistral Small 1.2won 7 · lost 2

Magistral Medium 1.2won 7 · lost 2

Mimo V2.5won 10 · lost 3

GPT OSS 20Bwon 8 · lost 3

O3 Miniwon 10 · lost 4

GPT-4.1 Miniwon 10 · lost 4

Claude Haiku 4.5won 10 · lost 4

GPT-5.4 Miniwon 9 · lost 4

Mimo V2.5 Prowon 9 · lost 4

Grok 4.20won 8 · lost 4

GPT-5.4 Nanowon 9 · lost 5

Grok 4.3won 9 · lost 5

Gemini 3.5 Flash Litewon 9 · lost 5

Nemotron 3 Ultrawon 7 · lost 4

Gemini 3.1 Flash Litewon 8 · lost 5

DeepSeek V3won 8 · lost 6

Mistral Large 3won 8 · lost 6

Qwen3.6 Pluswon 8 · lost 6

Claude 3.5 Sonnetwon 7 · lost 6

MiniMax M2.7won 7 · lost 6

Gemma 4 31Bwon 5 · lost 5

Grok 3won 6 · lost 6

Kimi K2won 7 · lost 7

MiniMax M3won 7 · lost 7

GLM-4.7won 7 · lost 7

DeepSeek R1won 6 · lost 7

GLM-4.6won 6 · lost 7

Qwen3.6 Maxwon 4 · lost 5

O4 Miniwon 6 · lost 8

Claude Sonnet 4won 6 · lost 8

Inkling Smallwon 6 · lost 8

GPT-4.1won 6 · lost 8

DeepSeek V3.2won 6 · lost 8

Inklingwon 6 · lost 8

GLM-5.1won 6 · lost 8

Kimi K2 Thinkingwon 5 · lost 7

Grok 3 Miniwon 5 · lost 8

Qwen3.5 Flashwon 5 · lost 8

Qwen3 235B A22B Instructwon 5 · lost 8

Qwen3 Maxwon 5 · lost 8

Claude 3.7 Sonnetwon 5 · lost 9

O1won 5 · lost 9

Gemini 2.5 Flashwon 5 · lost 9

Claude Opus 4won 5 · lost 9

Grok 4.1 Fastwon 5 · lost 9

Qwen3.8 27Bwon 5 · lost 9

Kimi K2.5won 5 · lost 9

Kimi K2.6won 5 · lost 9

GLM-5.3 Flashwon 5 · lost 9

GPT-5 Miniwon 4 · lost 10

MiniMax M2.5won 4 · lost 10

Grok 4 Fastwon 4 · lost 10

Gemini 2.5 Prowon 4 · lost 10

GPT-5.1won 4 · lost 10

GLM-5won 4 · lost 10

Qwen3.7 Maxwon 4 · lost 10

DeepSeek V4won 3 · lost 8

GLM-4.5won 3 · lost 8

Grok 4won 3 · lost 11

GPT-5.2won 3 · lost 11

DeepSeek V4 Flashwon 3 · lost 11

GPT-5.6 Lunawon 3 · lost 11

GLM-5.2won 3 · lost 11

GLM-5.3won 3 · lost 11

Gemini 3.1 Prowon 3 · lost 11

Qwen 3.5 Pluswon 2 · lost 9

DeepSeek V4.1 Flashwon 2 · lost 11

Muse Sparkwon 2 · lost 11

O3won 2 · lost 12

GPT-5won 2 · lost 12

Claude Sonnet 4.5won 2 · lost 12

DeepSeek V4 Prowon 2 · lost 12

Grok 4.5won 2 · lost 12

GPT-5.6 Terrawon 2 · lost 12

Gemini 3 Flashwon 2 · lost 12

Claude Opus 4.5won 2 · lost 12

Gemini 3.5 Flashwon 2 · lost 12

Gemini 3 Prowon 2 · lost 12

Mimo V2.6 Flashwon 1 · lost 8

Grok 4.7won 1 · lost 10

GPT-6 Lunawon 1 · lost 10

Claude Opus 4.1won 1 · lost 11

Muse Spark 1.2won 1 · lost 12

Grok 4.6won 1 · lost 13

Claude Sonnet 4.6won 1 · lost 13

Qwen3.8 Maxwon 1 · lost 13

Gemini 3.6 Flashwon 1 · lost 13

Kimi K3won 1 · lost 13

Muse Spark 1.1won 1 · lost 13

Gemini 3.8 Flashwon 1 · lost 13

Mimo V2.6 Prowon 0 · lost 9

Muse Spark 1.3won 0 · lost 10

GPT-6 Solwon 0 · lost 11

GPT-6 Astrawon 0 · lost 11

Claude Opus 5.5won 0 · lost 11

Claude Sonnet 5won 0 · lost 14

GPT-5.4won 0 · lost 14

Claude Opus 4.8won 0 · lost 14

GPT-5.5won 0 · lost 14

GPT-5.6 Solwon 0 · lost 14

Gemini 3.7 Flashwon 0 · lost 14

Claude Opus 5won 0 · lost 14

Claude Fable 5.1won 0 · lost 14

Claude Opus 4.7won 0 · lost 14

Claude Fable 5won 0 · lost 14

Claude Opus 4.6won 0 · lost 14

§ 3 · Sources

Where the numbers come from

3 publications, 13 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1385

SimpleBench ↗1 measureread 2026-09-26

SimpleBench 34.7%

Vals.ai ↗11 measuresread 2026-09-26

Vals · CaseLaw 55.84%Vals · LegalBench 75.45%Vals · CorpFin 58.9%Vals · TaxEval 66.35%Vals · MedQA 91.16%Vals · MedCode 34.08%Vals · MedScribe 80.78%Vals · SWE-bench Verified 74.8% (Mini-SWE-agent)Vals · GPQA Diamond 78.54%Vals · MMLU Pro 87.05%Vals · AIME 77.92%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=minimax-m2-1)](https://publicai.io/model-index/m/minimax-m2-1)