The LLM benchmark aggregator.

Qwen3.6 Plus

Alibaba

Strongest in Academic knowledge (#24 of 123), weakest in Core abilities (#187 of 204). Above par in 9 of 22 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Opus 4.7 and ahead of Claude Sonnet 4 and Claude Opus 4.

§ 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.

Knowledge56.7−6.8#27/1381/2

Academic knowledge58.1−5.8#24/1231/1

Human preference61.2−6.3#70/3421/1

Agents52.9−15.2#87/2681/5

Knowledge work54.4−19.2#58/1781/2

Reasoning48.3−18.6#99/1782/4

Science57.9−5.6#38/1221/1

Mathematics49.7−16#80/1402/2

Reasoning39−30.1#116/1401/3

Professional48.2−13.4#101/1681/1

Finance53.2−9.7#67/1511/1

Medical46.3−20.5#104/1401/1

Legal44−23.1#108/1511/1

Coding44.5−24.6#118/1652/5

Code generation51.6−18.4#41/771/2

Agentic coding42.4−26.3#126/1572/4

Core abilities40−27.4#187/2041/3

Language41.9−29.6#42/571/1

Data analysis44.1−22#46/571/1

Instruction following33.1−40.6#52/571/1

General intelligence40.5−29.6#171/2041/3

§ 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 Plus, left for the other.

GPT-4o Miniwon 17 · lost 1

GPT-4.1 Nanowon 16 · lost 2

Mistral Medium 3.5won 15 · lost 2

Mimo V2.5won 13 · lost 2

Claude 3.5 Haikuwon 12 · lost 2

Grok 4.3won 18 · lost 4

Qwen3.6 27Bwon 13 · lost 3

Gemini 2.5 Flash Litewon 11 · lost 3

Llama 4 Maverick Instructwon 14 · lost 4

GPT-5.4 Miniwon 16 · lost 5

Llama 4 Scout Instructwon 12 · lost 4

Command Awon 12 · lost 4

GPT-4owon 11 · lost 4

MiniMax M2.7won 11 · lost 4

Mistral Large 3won 13 · lost 5

Gemini 3.1 Flash Litewon 12 · lost 5

GPT-5.4 Nanowon 15 · lost 7

GPT OSS 20Bwon 10 · lost 5

GPT-5 Nanowon 10 · lost 5

GPT OSS 120Bwon 12 · lost 6

O3 Miniwon 11 · lost 6

Gemini 2.0 Flashwon 10 · lost 6

Grok 4.1 Fastwon 9 · lost 6

Gemini 3.5 Flash Litewon 13 · lost 9

DeepSeek V3won 11 · lost 8

Grok 4.20won 8 · lost 6

Claude 3.5 Sonnetwon 8 · lost 6

Nemotron 3 Ultrawon 9 · lost 7

Inkling Smallwon 9 · lost 7

GPT-4.1 Miniwon 10 · lost 8

Claude Haiku 4.5won 10 · lost 8

Inklingwon 12 · lost 10

Claude 3.7 Sonnetwon 8 · lost 7

Qwen3 Maxwon 8 · lost 7

GLM-4.6won 9 · lost 8

Claude Opus 4won 9 · lost 8

Claude Sonnet 4won 10 · lost 9

Grok 3won 7 · lost 7

Grok 4 Fastwon 8 · lost 8

GLM-4.7won 8 · lost 8

GPT-5 Miniwon 9 · lost 9

DeepSeek R1won 9 · lost 9

GPT-4.1won 8 · lost 9

Kimi K2won 8 · lost 9

Gemma 4 31Bwon 7 · lost 8

Qwen3.8 27Bwon 10 · lost 12

Gemini 2.5 Flashwon 8 · lost 10

DeepSeek V3.2won 8 · lost 10

MiniMax M2.1won 6 · lost 8

Qwen3 235B A22B Instructwon 7 · lost 10

Mimo V2.5 Prowon 7 · lost 10

MiniMax M3won 9 · lost 13

GPT-5won 7 · lost 11

Kimi K2.5won 7 · lost 11

MiniMax M2.5won 6 · lost 10

O1won 5 · lost 9

O4 Miniwon 6 · lost 12

O3won 6 · lost 12

DeepSeek V4 Flashwon 7 · lost 15

Grok 3 Miniwon 5 · lost 11

GPT-5.1won 5 · lost 11

Grok 4won 5 · lost 12

Kimi K2 Thinkingwon 4 · lost 10

Kimi K2.6won 6 · lost 16

GLM-5.3 Flashwon 6 · lost 16

Muse Sparkwon 4 · lost 11

GPT-6 Lunawon 5 · lost 14

Gemini 2.5 Prowon 5 · lost 14

GLM-5won 4 · lost 12

GLM-5.1won 4 · lost 12

GPT-5.2won 5 · lost 16

Claude Sonnet 4.5won 4 · lost 14

GPT-5.6 Lunawon 4 · lost 18

Grok 4.7won 3 · lost 16

Claude Opus 4.5won 3 · lost 18

DeepSeek V4 Prowon 3 · lost 19

Claude Sonnet 4.6won 3 · lost 19

Qwen3.7 Maxwon 3 · lost 19

GPT-5.4won 3 · lost 19

GLM-5.2won 3 · lost 19

Gemini 3.5 Flashwon 3 · lost 19

GLM-5.3won 3 · lost 19

Gemini 3.6 Flashwon 3 · lost 19

Gemini 3.1 Prowon 3 · lost 19

Muse Spark 1.1won 3 · lost 19

DeepSeek V4.1 Flashwon 2 · lost 19

Claude Sonnet 5won 2 · lost 20

Grok 4.5won 2 · lost 20

GPT-5.6 Terrawon 2 · lost 20

Gemini 3.8 Flashwon 2 · lost 20

Gemini 3 Flashwon 1 · lost 13

GPT-6 Solwon 1 · lost 18

Muse Spark 1.2won 1 · lost 20

Grok 4.6won 1 · lost 21

Qwen3.8 Maxwon 1 · lost 21

Claude Opus 4.8won 1 · lost 21

Gemini 3.7 Flashwon 1 · lost 21

Gemini 3 Prowon 0 · lost 17

Muse Spark 1.3won 0 · lost 18

GPT-6 Astrawon 0 · lost 19

Claude Opus 5.5won 0 · lost 19

Claude Opus 4.6won 0 · lost 20

GPT-5.5won 0 · lost 22

GPT-5.6 Solwon 0 · lost 22

Kimi K3won 0 · lost 22

Claude Opus 5won 0 · lost 22

Claude Fable 5.1won 0 · lost 22

Claude Opus 4.7won 0 · lost 22

Claude Fable 5won 0 · lost 22

§ 3 · Sources

Where the numbers come from

4 publications, 26 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1443

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 976

LiveBench ↗8 measuresread 2026-09-26

LiveBench 68.9LiveBench · Reasoning 75.8LiveBench · Coding 78.2LiveBench · Agentic Coding 41.4LiveBench · Mathematics 83.7LiveBench · Data Analysis 69.9LiveBench · Language 75LiveBench · Instruction Following 58.3

Vals.ai ↗16 measuresread 2026-09-26

Vals · Legal Research Bench 14.9%Vals · CaseLaw 51.45%Vals · LegalBench 84.23%Vals · Harvey Legal Agent Benchmark 1.25%Vals · Finance Agent 40.85%Vals · CorpFin 61.93%Vals · TaxEval 74.73%Vals · MortgageTax 67.97%Vals · MedCode 36.89%Vals · MedScribe 76.96%Vals · SWE-bench Verified 73.4% (Mini-SWE-agent)Vals · Vibe Code Bench 25.57% (OpenHands)Vals · Code Migration 11.1%Vals · GPQA Diamond 87.37%Vals · MMLU Pro 87.67%Vals · AIME 94.58%

Badge

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