Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Qwen3.6 27B

Alibaba · 28B · open weights

Strongest in Data analysis (#43 of 57), weakest in Core abilities (#204 of 204). Above par in 4 of 16 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Mistral Medium 3.5 and Grok 4.3.

§ 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.

Professional51#71/168
Finance54.8#47/151
Legal44#109/151
Agents51.8#99/268
Knowledge work52.3#65/178
Coding40.3#151/165
Code generation38.5#63/77
Agentic coding41#136/157
Reasoning35.2#171/178
Mathematics36.4#124/140
Reasoning31.8#139/140
Core abilities32.8#204/204
Data analysis44.9#43/57
Language26#56/57
Instruction following26#56/57
General intelligence34#197/204

§ 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 27B, left for the other.

GPT-4o Miniwon 9 · lost 3
Mercury 2.5won 8 · lost 3
Gemini 3.1 Flash Litewon 7 · lost 4
Grok 4.3won 9 · lost 7
Mistral Medium 3.5won 6 · lost 5
Command Awon 5 · lost 5
GPT-4.1 Nanowon 6 · lost 6
Mistral Large 3won 6 · lost 6
GPT OSS 120Bwon 6 · lost 6
GPT-5.4 Nanowon 8 · lost 8
Gemma 4 31Bwon 5 · lost 6
Nemotron 3 Ultrawon 5 · lost 7
Llama 4 Scout Instructwon 4 · lost 6
Grok 4.20won 4 · lost 6
DeepSeek V3won 5 · lost 8
DeepSeek R1won 5 · lost 8
Gemini 3.5 Flash Litewon 6 · lost 10
GPT-5.4 Miniwon 6 · lost 10
O3 Miniwon 4 · lost 7
Claude Haiku 4.5won 4 · lost 8
Kimi K2.5won 4 · lost 8
Claude Sonnet 4won 4 · lost 9
Inkling Smallwon 3 · lost 7
GPT-5.1won 3 · lost 7
Grok 4 Fastwon 3 · lost 7
GLM-4.6won 3 · lost 8
GPT-4.1 Miniwon 3 · lost 9
DeepSeek V3.2won 3 · lost 9
Grok Build 0.1won 3 · lost 10
GLM-4.7won 2 · lost 8
GLM-5.1won 2 · lost 8
Gemini 2.0 Flashwon 2 · lost 8
MiniMax M2.5won 2 · lost 8
Qwen3.6 Pluswon 3 · lost 13
Gemini 3.1 Prowon 3 · lost 13
Kimi K2won 2 · lost 9
Mimo V2.5 Prowon 2 · lost 9
Grok 4won 2 · lost 9
Claude Sonnet 4.5won 2 · lost 10
O4 Miniwon 2 · lost 10
GPT-5 Miniwon 2 · lost 10
Kimi K2.7 Codewon 2 · lost 11
Gemini 2.5 Prowon 2 · lost 11
MiniMax M3won 2 · lost 14
GPT-6 Lunawon 2 · lost 14
DeepSeek V4 Flashwon 2 · lost 14
Grok 4.5won 2 · lost 14
Grok 3 Miniwon 1 · lost 9
Kimi K2 Thinkingwon 1 · lost 9
GLM-5won 1 · lost 9
Ox Alphawon 1 · lost 10
Qwen3 235B A22B Instructwon 1 · lost 10
Claude Opus 4won 1 · lost 10
Gemini 2.5 Flashwon 1 · lost 11
O3won 1 · lost 11
GPT-5won 1 · lost 11
DeepSeek V4 Flash Visionwon 1 · lost 12
Claude Opus 4.6won 1 · lost 13
Kimi K2.6won 1 · lost 15
GLM-5.3 Flashwon 1 · lost 15
Inklingwon 1 · lost 15
Gemini 3.6 Flashwon 1 · lost 15
Qwen3.7 Maxwon 1 · lost 15
Gemini 3.5 Flashwon 1 · lost 15
Qwen3.8 27Bwon 1 · lost 15
GLM-5.3won 1 · lost 15
Claude Opus 4.8won 1 · lost 15
Gemini 3.8 Flashwon 1 · lost 15
Gemini 3.7 Flashwon 1 · lost 15
DeepSeek V4.1 Flashwon 1 · lost 15
Grok 4.7won 1 · lost 15
GPT-6 Solwon 1 · lost 15
GPT-6 Astrawon 1 · lost 15
GPT-5.2 Codexwon 0 · lost 11
GPT-4.1won 0 · lost 11
Union Alphawon 0 · lost 11
Mimo V2.6 Prowon 0 · lost 11
Gemini 3 Prowon 0 · lost 11
Qwen3.8 Flash Nextwon 0 · lost 13
Claude Opus 4.5won 0 · lost 15
GPT-5.2won 0 · lost 15
GPT-5.6 Lunawon 0 · lost 16
GLM-5.2won 0 · lost 16
Claude Sonnet 4.6won 0 · lost 16
Muse Spark 1.1won 0 · lost 16
Claude Sonnet 5won 0 · lost 16
DeepSeek V4 Prowon 0 · lost 16
Muse Spark 1.2won 0 · lost 16
Claude Opus 4.7won 0 · lost 16
GPT-5.6 Terrawon 0 · lost 16
Claude Opus 5won 0 · lost 16
GPT-5.4won 0 · lost 16
Grok 4.6won 0 · lost 16
Qwen3.8 Maxwon 0 · lost 16
Kimi K3won 0 · lost 16
GPT-5.6 Solwon 0 · lost 16
Claude Opus 5.5won 0 · lost 16
Muse Spark 1.3won 0 · lost 16
GPT-5.5won 0 · lost 16
Claude Fable 5.1won 0 · lost 16
Claude Fable 5won 0 · lost 16

§ 3 · Sources

Where the numbers come from

4 publications, 16 figures. Every one links to the page it was read from.

GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 973
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 813
LiveBench ↗8 measuresread 2026-09-26
LiveBench 64LiveBench · Reasoning 70.3LiveBench · Coding 71.8LiveBench · Agentic Coding 39.3LiveBench · Mathematics 79.9LiveBench · Data Analysis 70.4LiveBench · Language 63.3LiveBench · Instruction Following 53.2
Vals.ai ↗6 measuresread 2026-09-26
Vals · CaseLaw 53.16%Vals · CorpFin 62.31%Vals · TaxEval 71.26%Vals · MortgageTax 68.28%Vals · SWE-bench Verified 70% (Mini-SWE-agent)Vals · Vibe Code Bench 11.94% (OpenHands)

Badge

PublicAI Index badge for Qwen3.6 27B[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-6-27b)](https://publicai.io/model-index/m/qwen3-6-27b)