The LLM benchmark aggregator.

Qwen3.6 35B A3B

Alibaba · 36B · A3B · open weights

Strongest in Knowledge work (#84 of 178), weakest in General intelligence (#132 of 204). Above par in 3 of 14 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.6 Terra and K2 Horizon 375B A23B and ahead of Gemma 4 12B and G9v3 39A5B.

§ 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.

Agents50.1−18#118/2682/5

Knowledge work50.1−23.5#84/1782/2

Tool use41.3−32.7—/81✱0/1

Core abilities46.7−20.7#130/2041/3

General intelligence45.3−24.8#132/2041/3

Long context47.9−16.7—/0✱✱

Reasoning49−17.9—/178✱0/4

Science48.7−14.8—/122✱0/1

Expert reasoning45−15.9—/0✱✱

Coding50−19.1—/165✱0/5

Agentic coding50.3−18.4—/157✱0/4

Code generation49.5−20.5—/77✱0/2

Knowledge47.9−15.6—/138✱0/2

Factuality46.9−12.1—/0✱✱

§ 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 35B A3B, left for the other.

Mistral Medium 3.5won 9 · lost 0

GPT-4o Miniwon 10 · lost 0

Granite 4.2 3Bwon 10 · lost 1

GPT-4.1 Nanowon 9 · lost 1

NVIDIA Nemotron 3 Nano 4Bwon 8 · lost 1

Mistral Large 3won 8 · lost 1

Command Awon 7 · lost 2

Granite 4.2 8Bwon 8 · lost 3

Claude Haiku 4.5won 7 · lost 3

GPT-4.1 Miniwon 7 · lost 3

Qwen3.5 9Bwon 7 · lost 3

Granite 4.2 30Bwon 9 · lost 4

Nemotron 3 Superwon 9 · lost 4

K2 Horizon 0.9Bwon 6 · lost 3

GPT OSS 120Bwon 6 · lost 3

Grok 4.3won 6 · lost 4

Gemini 3.5 Flash Litewon 6 · lost 4

GPT-5.4 Miniwon 6 · lost 4

GPT-5.4 Nanowon 6 · lost 4

DeepSeek V3won 6 · lost 4

Llama 4 Maverick Instructwon 6 · lost 4

G9v3 39A5Bwon 7 · lost 5

Gemma 4 12Bwon 5 · lost 4

Qwen3.6 Pluswon 5 · lost 5

Kimi K2.6won 5 · lost 5

Gemini 3.1 Prowon 5 · lost 5

K2 Horizon 3.7Bwon 5 · lost 6

Gemini 3.1 Flash Litewon 4 · lost 5

MiniMax M3won 6 · lost 8

Gemini 2.5 Prowon 4 · lost 6

Nemotron 3 Ultrawon 5 · lost 9

Gemma 4 31Bwon 5 · lost 9

Mimo V2.5 Prowon 3 · lost 6

DeepSeek R1won 3 · lost 6

K2 Horizon 32Bwon 4 · lost 8

DeepSeek V3.2won 3 · lost 7

Qwen3.7 Maxwon 3 · lost 7

GPT-5 Miniwon 3 · lost 7

Claude Sonnet 4won 3 · lost 7

Inklingwon 4 · lost 10

K2 Horizon 7Bwon 3 · lost 8

Muse Glimmer-30Bwon 3 · lost 9

Kimi K2won 2 · lost 7

GPT-4.1won 2 · lost 7

Qwen3 235B A22B Instructwon 2 · lost 7

Kimi K2.5won 2 · lost 7

Gemini 3 Prowon 2 · lost 7

GLM-4.6won 2 · lost 8

Claude Sonnet 4.5won 2 · lost 8

Claude Opus 4.5won 2 · lost 8

GPT-5.2won 2 · lost 8

DeepSeek V4 Flashwon 2 · lost 9

Qwen3.8 27Bwon 2 · lost 12

GLM-5.3 Flashwon 1 · lost 9

Gemini 2.5 Flashwon 1 · lost 9

Gemini 3.5 Flashwon 1 · lost 9

O4 Miniwon 1 · lost 9

Gemini 3.8 Flashwon 1 · lost 9

Grok 4.5won 1 · lost 9

Grok 4.6won 1 · lost 9

Qwen3.8 Maxwon 1 · lost 9

DeepSeek V4.1 Flashwon 1 · lost 10

GPT-5.6 Lunawon 1 · lost 13

K2 Horizon MoVA 36B A4Bwon 1 · lost 13

Muse Spark 1.2won 0 · lost 9

GPT-5won 0 · lost 9

Grok 4won 0 · lost 9

Claude Sonnet 4.6won 0 · lost 10

Muse Spark 1.1won 0 · lost 10

Gemini 3.6 Flashwon 0 · lost 10

Claude Opus 4.8won 0 · lost 10

O3won 0 · lost 10

Claude Opus 4.7won 0 · lost 10

GPT-5.4won 0 · lost 10

Gemini 3.7 Flashwon 0 · lost 10

GPT-5.5won 0 · lost 10

Claude Fable 5.1won 0 · lost 10

Claude Fable 5won 0 · lost 10

GLM-5.3won 0 · lost 11

DeepSeek V4 Prowon 0 · lost 11

Claude Opus 5won 0 · lost 11

Kimi K3won 0 · lost 11

GPT-5.6 Solwon 0 · lost 11

GLM-5.2won 0 · lost 14

Claude Sonnet 5won 0 · lost 14

K2 Horizon 375B A23Bwon 0 · lost 14

GPT-5.6 Terrawon 0 · lost 14

§ 3 · Sources

Where the numbers come from

4 publications, 12 figures. Every one links to the page it was read from.

Artificial Analysis ↗1 measureread 2026-09-26

Artificial Analysis Intelligence Index 18

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 879

AA-Briefcase ↗1 measureread 2026-09-26

AA-Briefcase 711

✱✱ IFM — K2 Horizon launch ↗the model’s own publisher9 measuresread 2026-09-26

tau3-Banking 9.3%Terminal-Bench 2.1 44.9%SciCode 35.8%Humanity's Last Exam (without tools) 22.2%GPQA Diamond 84.1%CritPt 0.3%AA-LCR 66.7%AA-Omniscience Accuracy 18.8%AA-Omniscience Non-Hallucination 49.5%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-6-35b-a3b)](https://publicai.io/model-index/m/qwen3-6-35b-a3b)