Qwen2 VL 72B Instruct
Qwen2 VL 72B Instruct is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
37results on37benchmarks
- 37 vendor-reported
From 3 sources · latest Oct 6, 2026 · How verification works
Qwen2 VL 72B Instruct benchmark results
37 results on 37 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
42.0% behind the leader5 of 6 ranked benchmarks measured
- 87.70Oct 6, 2026
- 77.80Aug 25, 2026
- MathVista70.50Oct 6, 2026MathVista-Mini
- 64.50Aug 25, 2026
- 46.20Oct 6, 2026
Show 2 more multimodal resultsHide 2 multimodal results
- 68.30Aug 25, 2026
- 46.10Aug 25, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 91.93Oct 6, 2026
- 85.50Oct 6, 2026
- 77.80Oct 6, 2026
- 73.60Oct 6, 2026
- 30.90Oct 6, 2026
- 86.50Oct 6, 2026
Show 24 more resultsHide 24 results
- 75.80Aug 24, 2026
- 67.80Aug 24, 2026
- Avg.30.90Aug 24, 2026AVG
- 68.70Aug 25, 2026
- 88.30Oct 6, 2026
- 96.50Aug 25, 2026
- 96.50Oct 6, 2026
- 77.90Oct 6, 2026
- 77.90Aug 24, 2026
- 58.10Aug 24, 2026
- 84.50Aug 25, 2026
- 84.50Oct 6, 2026
- 25.90Aug 25, 2026
- 86.60Aug 24, 2026
- 86.50Aug 24, 2026
- 85.90Aug 24, 2026
- 1.70Aug 25, 2026
- 2482.70Aug 24, 2026
- MMMU (val) (Pass@1)64.50Aug 27, 2026MMMUval
- 71.70Aug 24, 2026
- 31.00Aug 24, 2026
- 85.50Aug 24, 2026
- 77.80Aug 24, 2026
- 71.20Aug 24, 2026
Qwen2 VL 72B Instruct: common questions
Who makes Qwen2 VL 72B Instruct?
Qwen2 VL 72B Instruct is made by Alibaba.
When was Qwen2 VL 72B Instruct released?
Qwen2 VL 72B Instruct's weights were first published on Hugging Face on Sep 17, 2024.
What is Qwen2 VL 72B Instruct good at?
Qwen2 VL 72B Instruct is behind the leaders in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
How many benchmarks has Qwen2 VL 72B Instruct been tested on?
We track 37 results for Qwen2 VL 72B Instruct on 37 benchmarks from 3 sources. The latest was recorded on Oct 6, 2026.
About this record
Where Qwen2 VL 72B Instruct's numbers come from, and every name it appears under.
- Tracked since
- Aug 24, 2026
- Newest source mention
- Aug 24, 2026
Where the results come from
Verification: 37 scores · 0 independently verified · 37 vendor-reported. How these tiers are assigned
From 3 sources on 2 sites. Hugging Face supplies 23 of them. Bars are coloured by trust tier.
- huggingface.co23
- api.llm-stats.com14