The LLM benchmark aggregator.

Qwen3.6 Max

Alibaba

Strongest in Finance (#34 of 162), weakest in Legal (#155 of 173). Above par in 5 of 9 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Claude Opus 5.5 and ahead of Step 5 and Grok 4.7.

§ 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.

Human preference62.4−6.4#53/3541/1

Reasoning52.8−12.6#69/1951/5

Reasoning54.5−14.5#46/1471/3

Coding49.7−16.4#91/1791/6

Agentic coding49.7−17#89/1731/5

Professional48.2−14.2#125/1941/2

Finance56.3−6.1#34/1621/1

Legal38.4−27.5#155/1731/1

§ 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 Qwen3.6 Max, left for the other.

Laguna XS.2won 6 · lost 0

Nemotron 3.5 Super VLwon 6 · lost 0

GPT OSS 20Bwon 6 · lost 0

Mistral Medium 3.1won 6 · lost 0

GPT-5 nanowon 7 · lost 0

GPT-4o miniwon 8 · lost 0

NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 8 · lost 0

Mistral Medium 3.5won 8 · lost 0

GPT-4.1 nanowon 9 · lost 0

GPT-5.4 miniwon 9 · lost 0

Llama 4 Maverick Instructwon 8 · lost 1

Gemini 2.0 Flashwon 8 · lost 1

GPT-5.4 nanowon 8 · lost 1

Claude Haiku 4.5won 8 · lost 1

GLM-4.7won 8 · lost 1

Gemma 4 31Bwon 8 · lost 1

Claude 3.5 Haikuwon 7 · lost 1

Command Awon 7 · lost 1

MiMo V2.5won 7 · lost 1

Llama 3.3 70B Instructwon 6 · lost 1

Llama 4 Scout Instructwon 6 · lost 1

O1 Miniwon 6 · lost 1

Gemini 1.5 Prowon 6 · lost 1

DeepSeek V3.1won 6 · lost 1

Qwen3.7 Pluswon 6 · lost 1

Mercury 2.5won 5 · lost 1

Laguna M.1won 5 · lost 1

Gemini 2.0 Flash Thinkingwon 5 · lost 1

Command R+won 5 · lost 1

Mistral Small 3.1 24B Instructwon 5 · lost 1

Gemini 1.5 Flashwon 5 · lost 1

Llama 3.1 405B Instructwon 5 · lost 1

Grok 2won 5 · lost 1

Gemini 2.5 Flash-Litewon 5 · lost 1

GPT-4owon 7 · lost 2

GPT OSS 120Bwon 7 · lost 2

GPT-4.1 miniwon 7 · lost 2

GPT-5 miniwon 7 · lost 2

MiniMax M2.5won 7 · lost 2

Grok 4 Fastwon 7 · lost 2

Inkling Smallwon 7 · lost 2

Mistral Large 3won 7 · lost 2

DeepSeek V3.2won 7 · lost 2

NVIDIA Nemotron 3 Ultra 550B A55Bwon 7 · lost 2

Inklingwon 7 · lost 2

Gemini 2.5 Prowon 7 · lost 2

Kimi K2.5won 7 · lost 2

Gemini 3.5 Flash-Litewon 7 · lost 2

Claude Sonnet 4.5won 7 · lost 2

GLM-5won 7 · lost 2

Claude 3.5 Sonnetwon 6 · lost 2

MiniMax M2.7won 6 · lost 2

Gemini 3.1 Flash-Litewon 6 · lost 2

Grok 4.3won 6 · lost 2

Qwen3.6 Pluswon 6 · lost 2

Kimi K2 Thinkingwon 5 · lost 2

GPT-4 Turbowon 5 · lost 2

Claude Opus 4.1won 5 · lost 2

Qwen3.6 27Bwon 4 · lost 2

Ling 3.0 Flashwon 4 · lost 2

GLM-4.5won 4 · lost 2

GPT-4.5won 4 · lost 2

O3 Miniwon 6 · lost 3

DeepSeek V3won 6 · lost 3

Grok 4.1 Fastwon 6 · lost 3

MiniMax M3won 6 · lost 3

GPT-5.1won 6 · lost 3

Qwen3.5 Flashwon 5 · lost 3

GLM-4.6won 5 · lost 3

MiMo V2.5 Prowon 5 · lost 3

Muse Spark Openwon 4 · lost 3

Grok 3 Miniwon 5 · lost 4

MiniMax M2.1won 5 · lost 4

Claude 3.7 Sonnetwon 5 · lost 4

O4 Miniwon 5 · lost 4

O1won 5 · lost 4

Claude Sonnet 4won 5 · lost 4

Gemini 2.5 Flashwon 5 · lost 4

Grok 3won 5 · lost 4

GPT-4.1won 5 · lost 4

Kimi K2won 5 · lost 4

DeepSeek R1won 5 · lost 4

Qwen3 235B A22B Instructwon 5 · lost 4

Mistral Large 4won 5 · lost 4

Claude Opus 4won 5 · lost 4

O3won 5 · lost 4

Qwen3.8 27Bwon 5 · lost 4

GPT-6 Lunawon 5 · lost 4

Grok 4.7won 5 · lost 4

Step 5won 5 · lost 4

Qwen 3.5 Pluswon 3 · lost 3

Beam 1.0won 3 · lost 3

Qwen3 Maxwon 4 · lost 4

MiMo V2.6 Flashwon 4 · lost 4

Kimi K2.6won 4 · lost 4

Grok 4won 4 · lost 5

Claude Haiku 5.5won 4 · lost 5

GPT-5won 4 · lost 5

DeepSeek V4 Flashwon 4 · lost 5

GPT-5.6 Lunawon 4 · lost 5

GLM-5.1won 4 · lost 5

Grok 4.20won 4 · lost 5

Gemini 3 Flashwon 4 · lost 5

DeepSeek V4won 2 · lost 4

MiniMax M3.1 Flashwon 2 · lost 4

Ember 1won 2 · lost 4

GPT-5.2won 3 · lost 6

Grok 4.6won 3 · lost 6

GPT-6 Solwon 3 · lost 6

Qwen3.7 Maxwon 3 · lost 6

Claude Opus 4.5won 3 · lost 6

GLM-5.2won 3 · lost 6

MiMo V2.6 Prowon 3 · lost 6

Gemini 3 Prowon 3 · lost 6

Gemini 3.1 Prowon 3 · lost 6

Inkling 2 Smallwon 2 · lost 6

Muse Sparkwon 2 · lost 6

DeepSeek V4 Prowon 2 · lost 7

GLM-5.3 Flashwon 2 · lost 7

Gemini 3.5 Flashwon 2 · lost 7

GLM-5.3won 2 · lost 7

Hy4won 1 · lost 5

GPT-6.1 Terrawon 1 · lost 5

Muse Spark 1.1won 1 · lost 7

Claude Sonnet 5won 1 · lost 8

Grok 4.5won 1 · lost 8

Claude Sonnet 4.6won 1 · lost 8

GPT-6 Astrawon 1 · lost 8

DeepSeek V4.1 Flashwon 1 · lost 8

GPT-6.1 Solwon 1 · lost 8

Gemini 3.6 Flashwon 1 · lost 8

Qwen3.8 Maxwon 1 · lost 8

Muse Spark 1.2won 1 · lost 8

Muse Wonderwon 1 · lost 8

Muse Emberwon 0 · lost 6

Claude Fable 5.2won 0 · lost 6

Muse Wonder Fullwon 0 · lost 6

Kimi K3.1 Prowon 0 · lost 8

Gemini 4 Carbonwon 0 · lost 8

GPT-5.6 Terrawon 0 · lost 9

Claude Sonnet 5.5won 0 · lost 9

GPT-5.4won 0 · lost 9

GPT-5.5won 0 · lost 9

Claude Opus 4.8won 0 · lost 9

GPT-5.6 Solwon 0 · lost 9

Kimi K3won 0 · lost 9

Gemini 3.7 Flashwon 0 · lost 9

Claude Opus 5won 0 · lost 9

Muse Spark 1.3won 0 · lost 9

Gemini 3.8 Flashwon 0 · lost 9

Claude Opus 4.7won 0 · lost 9

Claude Fable 5.1won 0 · lost 9

Claude Opus 4.6won 0 · lost 9

Claude Fable 5won 0 · lost 9

Claude Opus 5.5won 0 · lost 9

Gemini 4 Argonwon 0 · lost 9

§ 3 · Sources

Where the numbers come from

3 publications, 5 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-11

LMArena Text 1460

SimpleBench ↗1 measureread 2026-11-11

SimpleBench 63%

Vals.ai ↗3 measuresread 2026-11-11

Vals · CaseLaw 47.91%Vals · CorpFin 66.47%Vals · SWE-bench Verified 72.8% (Mini-SWE-agent)

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-6-max)](https://publicai.io/model-index/m/qwen3-6-max)