Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Qwen2.5 Vl 72B Instruct

Alibaba · 73B · open weights

Strongest in Computer use (#67 of 69, on 1 of its 2 boards), weakest in Agents (#278 of 298). Above par in 0 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Carbon and Claude Fable 5 and ahead of K-EXAONE 2.0 and GPT-4.1 nano.

§ 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.

Core abilities44.3#155/201
General intelligence41.8#147/181
Agents40.7#278/298
Computer use31.5#67/69

§ 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 Qwen2.5 Vl 72B Instruct, left for the other.

Granite 4.2 3Bwon 3 · lost 0
Gemma 4 31Bwon 4 · lost 0
Smaug Nemotron 3.5won 3 · lost 1
NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 2 · lost 1
Gemma 3 4B ITwon 2 · lost 1
Nemotron 3 Nano 4Bwon 2 · lost 1
Mistral Small 4won 2 · lost 1
North Mini Codewon 2 · lost 1
GPT-4o miniwon 2 · lost 1
Command Awon 2 · lost 1
Mistral Medium 3.5won 2 · lost 1
Granite 4.2 8Bwon 2 · lost 1
Command A+won 2 · lost 1
Muse Glimmerwon 2 · lost 1
GPT-4.1 nanowon 2 · lost 1
K-EXAONE 2.0won 2 · lost 1
UI-TARS 1.5 7Bwon 2 · lost 2
Nemotron 3.5 Super VLwon 2 · lost 2
Inklingwon 2 · lost 2
GPT-5.4 miniwon 1 · lost 2
GPT-5.4 nanowon 1 · lost 2
GPT-5.6 Lunawon 1 · lost 2
Gemma 3 27B ITwon 1 · lost 2
DeepSeek V3won 1 · lost 2
Qwen3 30B A3B Thinkingwon 1 · lost 2
DeepSeek R1won 1 · lost 2
Muse Spark Openwon 1 · lost 3
Claude Haiku 5.5won 1 · lost 3
MiniMax M3won 1 · lost 3
Mistral Large 4won 1 · lost 3
GPT-6 Lunawon 1 · lost 3
Gemini 3.5 Flash-Litewon 0 · lost 3
Llama 4 Scout Instructwon 0 · lost 3
Inkling Smallwon 0 · lost 3
Apodex 1.1won 0 · lost 3
Solar Pro 4won 0 · lost 3
GPT OSS 120Bwon 0 · lost 3
Mistral Small 3.2won 0 · lost 3
Gemini 2.5 Flash-Litewon 0 · lost 3
Claude Sonnet 4.6won 0 · lost 3
Kimi K2.6won 0 · lost 3
Beam 1.0won 0 · lost 3
K2 Horizon 375B A23Bwon 0 · lost 3
NVIDIA Nemotron 3 Ultra 550B A55Bwon 0 · lost 3
JT-4.1 Flash 236B A21Bwon 0 · lost 3
GLM-4.6won 0 · lost 3
Nanbeige4.3 33Bwon 0 · lost 3
GLM-5.2won 0 · lost 3
GPT-4.1 miniwon 0 · lost 3
Qwen3 14Bwon 0 · lost 3
DeepSeek V4 Flashwon 0 · lost 3
Muse Spark 1.1won 0 · lost 3
Agnes 2.5 Pro Thetawon 0 · lost 3
Mistral Large 3won 0 · lost 3
DeepSeek V3.2won 0 · lost 3
Kimi K2won 0 · lost 3
GPT-4.1won 0 · lost 3
GPT OSS 20Bwon 0 · lost 3
MiMo V2.6 Flashwon 0 · lost 3
DeepSeek V4 Prowon 0 · lost 3
Qwen3 32Bwon 0 · lost 3
Qwen3 235B A22B Instructwon 0 · lost 3
Llama 4 Maverick Instructwon 0 · lost 3
Gemini 2.5 Flashwon 0 · lost 3
Ling 3.1 Flashwon 0 · lost 3
GPT-5.2won 0 · lost 3
DeepSeek V3.1 Terminuswon 0 · lost 3
Inkling 2 Smallwon 0 · lost 3
Claude Opus 5won 0 · lost 3
GLM-5.3won 0 · lost 3
Tencent Hy4won 0 · lost 3
GPT-5 nanowon 0 · lost 3
Muse Emberwon 0 · lost 3
Claude Opus 4.5won 0 · lost 3
Qwen3.8 Flash Nextwon 0 · lost 3
Claude Opus 4.7won 0 · lost 3
Qwen3 Next 80B A3B Thinkingwon 0 · lost 3
GPT-5.4won 0 · lost 3
Gemini 3.1 Flash-Litewon 0 · lost 3
O4 Miniwon 0 · lost 3
Qwen3 235B A22B Thinkingwon 0 · lost 3
Gemini 2.5 Prowon 0 · lost 3
GPT-5 miniwon 0 · lost 3
GPT-5won 0 · lost 3
Grok 4won 0 · lost 3
Qwen3.5 397B A17Bwon 0 · lost 3
GPT-5.6 Solwon 0 · lost 3
Muse Wonder Fullwon 0 · lost 3
Grok 4.5won 0 · lost 3
Gemini 3 Prowon 0 · lost 3
Claude Opus 4.8won 0 · lost 3
GPT-5.5won 0 · lost 3
Step 5won 0 · lost 4
GLM-5.3 Flashwon 0 · lost 4
Qwen3.8 27Bwon 0 · lost 4
MiniMax M3.1 Flashwon 0 · lost 4
MiMo V2.6 Prowon 0 · lost 4
GPT-5.6 Terrawon 0 · lost 4
Claude Sonnet 4.5won 0 · lost 4
Gemini 3.8 Flashwon 0 · lost 4
Grok 4.6won 0 · lost 4
Qwen3.8 Maxwon 0 · lost 4
Claude Sonnet 5.5won 0 · lost 4
DeepSeek V4.1 Flashwon 0 · lost 4
O3won 0 · lost 4
Kimi K3won 0 · lost 4
Grok 4.7won 0 · lost 4
Kimi K3.1 Prowon 0 · lost 4
Claude Sonnet 4won 0 · lost 4
Muse Spark 1.3won 0 · lost 4
Muse Wonderwon 0 · lost 4
Kimi K2.5won 0 · lost 4
Claude Opus 5.5won 0 · lost 4
Claude Fable 5.1won 0 · lost 4
GPT-6.1 Terrawon 0 · lost 4
Gemini 4 Argonwon 0 · lost 4
GPT-6.1 Solwon 0 · lost 4
Claude Fable 5.2won 0 · lost 4
GPT-6 Astrawon 0 · lost 4
Claude Fable 5won 0 · lost 4
Gemini 4 Carbonwon 0 · lost 4

§ 3 · Sources

Where the numbers come from

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

OSWorld ↗1 measureread 2026-11-12
OSWorld 5%
Kagi LLM Benchmark ↗1 measureread 2026-11-12
Kagi LLM Benchmark 36%

Badge

PublicAI Index badge for Qwen2.5 Vl 72B Instruct[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen2-5-vl-72b-instruct)](https://publicai.io/model-index/m/qwen2-5-vl-72b-instruct)