The LLM benchmark aggregator.

Qwen3.5 9B

Alibaba · 9.7B · open weights

Strongest in Knowledge work (#109 of 178, on 1 of its 2 boards), weakest in Agents (#159 of 268). Above par in 3 of 11 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.6 Terra and Claude Opus 5 and ahead of MiniMax M3 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.

Agents46.5−21.6#159/2681/5

Knowledge work44.7−28.9#109/1781/2

Tool use39.4−34.6—/81✱0/1

Core abilities49−18.4—/204✱0/3

Long context46.1−18.5—/0✱✱

Reasoning52.5−14.4—/178✱0/4

Mathematics54.5−11.2—/140✱0/2

Expert reasoning55.7−5.2—/0✱✱

Coding49−20.1—/165✱0/5

Agentic coding49.6−19.1—/157✱0/4

Code generation44.3−25.7—/77✱0/2

§ 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 Qwen3.5 9B, left for the other.

Qwen3.5 0.8Bwon 7 · lost 0

Mercury 2.5won 7 · lost 0

Mistral Large 3won 7 · lost 0

GPT-4o Miniwon 8 · lost 0

Granite 4.2 3Bwon 9 · lost 1

NVIDIA Nemotron 3 Nano 4Bwon 8 · lost 1

GPT-4.1 Nanowon 7 · lost 1

Nemotron 3 Ultrawon 8 · lost 2

Qwen3.5 4Bwon 6 · lost 2

G9v3 3Bwon 6 · lost 2

Qwen3.6 27Bwon 6 · lost 2

Grok 4.3won 6 · lost 2

GPT-5.4 Miniwon 6 · lost 2

Kimi K2.7 Codewon 6 · lost 2

Nemotron 3 Ultra 550B A55Bwon 6 · lost 2

K2 Horizon 0.9Bwon 6 · lost 2

Grok Build 0.1won 6 · lost 2

GPT-4.1 Miniwon 6 · lost 2

DeepSeek V3won 6 · lost 2

Llama 4 Maverick Instructwon 6 · lost 2

Granite 4.2 8Bwon 8 · lost 3

Command Awon 5 · lost 2

Mistral Medium 3.5won 5 · lost 2

Inklingwon 7 · lost 4

Gemini 3.5 Flash Litewon 5 · lost 3

GPT-5.4 Nanowon 5 · lost 3

Qwen3.6 Pluswon 5 · lost 3

Claude Haiku 4.5won 5 · lost 3

Qwen3.5 2Bwon 4 · lost 3

GPT OSS 120Bwon 4 · lost 3

Mimo V2.5 Prowon 4 · lost 3

Gemini 3.1 Flash Litewon 4 · lost 3

Nemotron 3 Superwon 5 · lost 4

G9v3 39A5Bwon 5 · lost 4

MiniMax M3won 6 · lost 5

Kimi K2.6won 4 · lost 4

Qwen3.7 Maxwon 4 · lost 4

DeepSeek R1won 4 · lost 4

DeepSeek V4 Flash Visionwon 4 · lost 4

Granite 4.2 30Bwon 5 · lost 5

Gemma 4 12Bwon 5 · lost 5

K2 Horizon 32Bwon 4 · lost 5

O3 Miniwon 3 · lost 4

Kimi K2.5won 3 · lost 4

K2 Horizon 3.7Bwon 4 · lost 6

Gemma 4 31Bwon 4 · lost 6

GPT-6 Lunawon 3 · lost 5

GLM-5.3 Flashwon 3 · lost 5

GLM-4.6won 3 · lost 5

DeepSeek V3.2won 3 · lost 5

Claude Sonnet 4.5won 3 · lost 5

Qwen3.8 Flash Nextwon 3 · lost 5

Gemini 2.5 Prowon 3 · lost 5

GPT-5 Miniwon 3 · lost 5

Gemini 3.1 Prowon 3 · lost 5

Qwen3.6 35B A3Bwon 3 · lost 7

Kimi K2won 2 · lost 5

GPT-4.1won 2 · lost 5

Gemini 3 Prowon 2 · lost 5

GLM-5.2won 3 · lost 8

K2 Horizon 7Bwon 3 · lost 8

Qwen3.8 27Bwon 3 · lost 8

Claude Sonnet 4.6won 2 · lost 6

Muse Spark 1.1won 2 · lost 6

Gemini 2.5 Flashwon 2 · lost 6

Claude Opus 4.5won 2 · lost 6

Gemini 3.8 Flashwon 2 · lost 6

Claude Sonnet 4won 2 · lost 6

Grok 4.5won 2 · lost 6

Grok 4.7won 2 · lost 6

Qwen3.8 Maxwon 2 · lost 6

DeepSeek V4 Flashwon 2 · lost 7

GLM-5.3won 2 · lost 7

Muse Glimmer-30Bwon 2 · lost 7

Kimi K3won 2 · lost 7

K2 Horizon MoVA 36B A4Bwon 2 · lost 8

K2 Horizon 375B A23Bwon 2 · lost 8

GPT-5.6 Lunawon 2 · lost 9

Qwen3 235B A22B Instructwon 1 · lost 6

Gemini 3.6 Flashwon 1 · lost 7

Gemini 3.5 Flashwon 1 · lost 7

O4 Miniwon 1 · lost 7

O3won 1 · lost 7

Muse Spark 1.2won 1 · lost 7

Grok 4.6won 1 · lost 7

DeepSeek V4 Prowon 1 · lost 8

DeepSeek V4.1 Flashwon 1 · lost 8

GPT-5.6 Solwon 1 · lost 8

Claude Sonnet 5won 1 · lost 10

GPT-5won 0 · lost 7

Grok 4won 0 · lost 7

Mimo V2.6 Prowon 0 · lost 7

GPT-5.2won 0 · lost 8

Claude Opus 4.8won 0 · lost 8

Claude Opus 4.7won 0 · lost 8

GPT-5.4won 0 · lost 8

Gemini 3.7 Flashwon 0 · lost 8

GPT-6 Solwon 0 · lost 8

Claude Opus 5.5won 0 · lost 8

Muse Spark 1.3won 0 · lost 8

GPT-5.5won 0 · lost 8

Claude Fable 5.1won 0 · lost 8

GPT-6 Astrawon 0 · lost 8

Claude Fable 5won 0 · lost 8

Claude Opus 5won 0 · lost 9

GPT-5.6 Terrawon 0 · lost 11

§ 3 · Sources

Where the numbers come from

2 publications, 8 figures. Every one links to the page it was read from.

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 407

✱✱ IFM — K2 Horizon launch ↗the model’s own publisher7 measuresread 2026-09-26

tau3-Banking 7%Terminal-Bench 2.1 29.2%SciCode 27.5%AA-LCR 65.3%SWE-bench Verified 50.8%HMMT Feb 2026 65.7%HLE 14.9%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-5-9b)](https://publicai.io/model-index/m/qwen3-5-9b)