The LLM benchmark aggregator.

Qwen3.5 397B A17B

Alibaba · 403B · A17B · open weights

Strongest in Fairness (#16 of 300, on 1 of its 2 boards), weakest in Jailbreak resistance (#173 of 272). Above par in 10 of 12 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Claude Opus 5.5 and ahead of O4 Mini and Phi 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.

Safety56.7−4.8#27/3371/3

Fairness68.2−1.8#16/3001/2

Secure code63.7−2.8#24/2741/1

Toxicity avoidance55.3−3.7#97/2721/1

Harm refusal52.5−9.1#119/3001/2

Jailbreak resistance51.3−13.6#173/2721/1

Core abilities52.7−14.7#64/2042/3

General intelligence53.5−16.6#70/2042/3

Human preference61.1−6.4#71/3421/1

Agents47.9−20.2#141/2682/5

Knowledge work47.2−26.4#95/1782/2

§ 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 397B A17B, left for the other.

Magistral Smallwon 8 · lost 0

Jamba Mini 1.7won 8 · lost 0

Jamba Large 1.7won 8 · lost 0

Smollm2 1.7B Instructwon 8 · lost 0

Zephyr 7B Betawon 8 · lost 0

Gemma 7B Itwon 8 · lost 0

DeepSeek LLM 67B Chatwon 8 · lost 0

Qwen1.5 14B Chatwon 8 · lost 0

Gemma 2 2B Itwon 8 · lost 0

Jamba 1.5 Miniwon 8 · lost 0

Qwen3.5 27Bwon 8 · lost 0

Qwen3 Vl 235B A22B Instructwon 8 · lost 0

Gemma 4 12Bwon 9 · lost 0

Llama 3.1 8B Instructwon 10 · lost 0

Magistral Mediumwon 10 · lost 0

GLM-4.5won 10 · lost 0

DeepSeek V3won 12 · lost 0

Qwen3.5 122B A10Bwon 12 · lost 0

GPT OSS 20Bwon 11 · lost 1

Gemma 3 27B Itwon 11 · lost 1

Gemma 3 4B Itwon 10 · lost 1

Gemini 2.5 Flashwon 10 · lost 1

NVIDIA Nemotron 3 Super 120B A12Bwon 9 · lost 1

Gemini 2.0 Flashwon 9 · lost 1

Gemma 4 26B A4Bwon 9 · lost 1

Grok 4.1 Fastwon 8 · lost 1

Phi-4 Mini Instructwon 7 · lost 1

Gemma 4 E2Bwon 7 · lost 1

Gemma 4 E4Bwon 7 · lost 1

Qwen3 8Bwon 7 · lost 1

Nous Hermes 2 Mixtral 8x7b Dpowon 7 · lost 1

Starling Lm 7B Betawon 7 · lost 1

DBRX Instructwon 7 · lost 1

GPT-3.5 Turbowon 7 · lost 1

Mistral Small 24B Instructwon 7 · lost 1

Command R Pluswon 7 · lost 1

Jamba 1.5 Largewon 7 · lost 1

Gemini 1.5 Flashwon 7 · lost 1

QwQ 32Bwon 7 · lost 1

Gemini 2.0 Flash Litewon 7 · lost 1

Gemini 2.5 Flash Litewon 7 · lost 1

Llama 4 Scout Instructwon 10 · lost 2

GPT-4.1 Nanowon 10 · lost 2

GLM-4.6won 10 · lost 2

DeepSeek V3.2won 10 · lost 2

DeepSeek V4 Flashwon 10 · lost 2

Grok 4.3won 10 · lost 2

Command Awon 9 · lost 2

Mistral Smallwon 9 · lost 2

Kimi K2won 9 · lost 2

Kimi K2.7 Codewon 8 · lost 2

Nemotron 3 Ultra 550B A55Bwon 8 · lost 2

Grok Build 0.1won 8 · lost 2

Ling 3.0 Flash VLwon 8 · lost 2

GPT-4won 8 · lost 2

Llama 3 70B Instructwon 8 · lost 2

Gemma 3 12B Itwon 8 · lost 2

O3 Miniwon 8 · lost 2

Grok 3won 8 · lost 2

Llama 3.2 3B Instructwon 7 · lost 2

Nova Microwon 7 · lost 2

Nova Prowon 7 · lost 2

Mistral Largewon 7 · lost 2

Qwen3 30B A3B Instructwon 7 · lost 2

Gemma 2B Itwon 6 · lost 2

Phi 3 Mini 128k Instructwon 6 · lost 2

Phi 3 Mini 4k Instructwon 6 · lost 2

Mistral 7B Instruct V0.2won 6 · lost 2

Granite 3.0 2B Instructwon 6 · lost 2

Phi 3 Small 8k Instructwon 6 · lost 2

Granite 3.1 2B Instructwon 6 · lost 2

Granite 3.0 8B Instructwon 6 · lost 2

Phi 3 Medium 4k Instructwon 6 · lost 2

Llama 3 8B Instructwon 6 · lost 2

Nova Litewon 6 · lost 2

Gemma 2 9B Itwon 6 · lost 2

O1 Miniwon 6 · lost 2

Gemini 1.5 Prowon 6 · lost 2

Mimo V2.6 Flashwon 6 · lost 2

GPT-4o Miniwon 9 · lost 3

Llama 4 Maverick Instructwon 9 · lost 3

GPT-4.1 Miniwon 9 · lost 3

DeepSeek R1won 9 · lost 3

MiniMax M3won 9 · lost 3

GPT-6 Lunawon 9 · lost 3

Grok 4won 8 · lost 3

GPT-4.1won 8 · lost 3

Claude 3 Haikuwon 7 · lost 3

Qwen3.5 35B A3Bwon 7 · lost 3

Llama 3.2 1B Instructwon 6 · lost 3

Granite 3.1 8B Instructwon 6 · lost 3

Qwen3 Next 80B A3B Thinkingwon 6 · lost 3

Claude 3.7 Sonnetwon 6 · lost 3

GPT OSS 120Bwon 8 · lost 4

Gemini 2.5 Prowon 8 · lost 4

Gemma 4 31Bwon 8 · lost 4

Kimi K2.6won 8 · lost 4

Qwen3.7 Maxwon 8 · lost 4

GLM-5.2won 8 · lost 4

Gemini 3.5 Flashwon 8 · lost 4

Gemini 3.6 Flashwon 8 · lost 4

Qwen3 235B A22B Instructwon 7 · lost 4

Ling 3.0 Flashwon 5 · lost 3

Kimi K2 Thinkingwon 5 · lost 3

Llama 3.1 Tulu 3 8Bwon 5 · lost 3

C4ai Aya Expanse 8Bwon 5 · lost 3

Qwen2 72B Instructwon 5 · lost 3

C4ai Aya Expanse 32Bwon 5 · lost 3

Claude 3 Sonnetwon 5 · lost 3

Qwen2.5 72B Instructwon 5 · lost 3

Qwen Maxwon 5 · lost 3

GPT-4owon 5 · lost 3

O1won 5 · lost 3

Claude Haiku 4.5won 7 · lost 5

Mimo V2.5 Prowon 7 · lost 5

Phi 4won 5 · lost 4

O4 Miniwon 6 · lost 5

Gemma 2 27B Itwon 4 · lost 4

Claude 3 Opuswon 4 · lost 4

GPT-4 Turbowon 4 · lost 4

Claude 3.5 Sonnetwon 4 · lost 4

Claude Opus 4.6won 4 · lost 4

Claude 3.5 Haikuwon 5 · lost 5

MiniMax M2won 5 · lost 5

Claude Opus 4won 5 · lost 5

Claude Sonnet 4.6won 5 · lost 5

Kimi K2.5won 6 · lost 6

GPT-5.6 Lunawon 6 · lost 6

GPT-6 Solwon 6 · lost 6

GLM-5.3 Flashwon 6 · lost 6

Gemini 3.8 Flashwon 6 · lost 6

O3won 5 · lost 6

GPT-5.2won 5 · lost 6

GPT-5 Miniwon 5 · lost 7

Claude Sonnet 4won 5 · lost 7

Inklingwon 5 · lost 7

Hy3won 5 · lost 7

Claude Sonnet 4.5won 5 · lost 7

DeepSeek V4 Prowon 5 · lost 7

Muse Spark 1.1won 5 · lost 7

GLM-5.1won 4 · lost 6

Gemini 3 Prowon 3 · lost 5

GPT-5 Nanowon 4 · lost 7

GPT-5won 4 · lost 8

Qwen3.8 Maxwon 4 · lost 8

Mimo V2.6 Prowon 4 · lost 8

GPT-5.6 Solwon 4 · lost 8

Grok 4.5won 3 · lost 9

GPT-5.6 Terrawon 3 · lost 9

GPT-5.4won 3 · lost 9

GPT-5.5won 3 · lost 9

Claude Opus 4.7won 3 · lost 9

MiniMax M2.7won 2 · lost 8

GPT-5.1won 2 · lost 8

Grok 4.7won 2 · lost 10

Claude Sonnet 5won 2 · lost 10

Grok 4.6won 1 · lost 11

Claude Opus 4.8won 1 · lost 11

Claude Opus 5.5won 1 · lost 11

Claude Opus 5won 0 · lost 12

§ 3 · Sources

Where the numbers come from

6 publications, 11 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1442

Artificial Analysis ↗1 measureread 2026-09-26

Artificial Analysis Intelligence Index 18

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 780

AA-Briefcase ↗1 measureread 2026-09-26

AA-Briefcase 561

Kagi LLM Benchmark ↗1 measureread 2026-09-26

Kagi LLM Benchmark 73.7%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 11.7%Enkrypt · Harmful content risk 2.8%Enkrypt · CBRN risk 24.5%Enkrypt · Toxicity risk 2.6%Enkrypt · Bias risk 49.6%Enkrypt · Insecure code risk 5.8%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-5-397b-a17b)](https://publicai.io/model-index/m/qwen3-5-397b-a17b)