Alibaba (Qwen), open weights
Qwen2.5-VL 72B Instruct
Qwen2.5-VL 72B Instruct by Alibaba (Qwen) ranks 302nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.9. Its strongest category is multimodal, where it ranks 97th. API pricing starts at $2.80 per million input tokens and $8.40 per million output tokens, with a 131K-token context window.
Last verified
Specifications
- Noometry rank
- #302 of 354
- Index score
- 29.9
- Evidence
- Confirmed 6 results
- Provider
Alibaba (Qwen)- Released
- September 1, 2024
- Weights
- Open weights
- Reasoning
- No
- Context window
- 131K
- Max output
- 8K
- Input price
- $2.80 / M
- Output price
- $8.40 / M
- Blended price
- $4.20 / M
- Output speed
- 43 tokens/s Kagi
- Value
- #197 of 219
- Knowledge cutoff
- April 2024
- Input
- text, image
- Hugging Face
- Qwen/Qwen2.5-VL-72B-Instruct
Category scores
Each category score combines every public result we have in that category.
- Agentic & Tool Use 18.6
- Reasoning 20.7
- Multimodal 33.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Agentic & Tool Use | 18.6 | #144 | 1 |
| Reasoning | 20.7 | #233 | 1 |
| Multimodal | 33.5 | #97 | 3 |
Strengths and weaknesses
Categories where Qwen2.5-VL 72B Instruct places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 20.7 | −2.9 | #233 of 350, top 67% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 18.6 | −11.7 | #144 of 154, top 94% |
Closest competitors
The models ranked just above and below Qwen2.5-VL 72B Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Palm 2 | #298 | 30.0 | — | — | Compare |
| Gemma 7B | #299 | 30.0 | — | — | Compare |
| Qwen2-72B | #300 | 30.0 | — | — | Compare |
| Gemini 1.5 Flash 8B | #301 | 29.9 | — | — | Compare |
| Mistral | #303 | 29.9 | — | — | Compare |
| OLMo 2 Furious 13B | #304 | 29.7 | — | — | Compare |
| Phi 3 Mini 128k Instruct | #305 | 29.7 | — | — | Compare |
| phi-3-medium 14B | #306 | 29.7 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OSWorld | 5% | #8 of 8, top 100% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 36% | #87 of 99, top 88% | Kagi LLM Benchmark |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1107 | #106 of 122, top 87% | LMArena | 2026-10-09 | |
| Video-MME | 73.5% | #4 of 15, top 27% | Epoch AI | ||
| GeoBench | 62% | #17 of 25, top 68% | Epoch AI | ||
| SpatialViz-Bench | 33.3% | #6 of 8, top 75% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $2.80 | $8.40 | — | 2026-10-10 |
| openrouter | $0.80 | $1 | $0.40 | 2026-10-10 |
Compare Qwen2.5-VL 72B Instruct
- Qwen2.5-VL 72B Instruct vs Gemini 1.5 Flash 8B
- Qwen2.5-VL 72B Instruct vs Mistral
- Qwen2.5-VL 72B Instruct vs Qwen2-72B
- Qwen2.5-VL 72B Instruct vs OLMo 2 Furious 13B
- Qwen2.5-VL 72B Instruct vs Gemma 7B
- Qwen2.5-VL 72B Instruct vs Phi 3 Mini 128k Instruct
- Qwen2.5-VL 72B Instruct vs GPT-6 Astra
- Qwen2.5-VL 72B Instruct vs Claude Fable 5.1
- Qwen2.5-VL 72B Instruct vs Gemini 3.8 Flash
- Qwen2.5-VL 72B Instruct vs Kimi K3
- Qwen2.5-VL 72B Instruct vs Grok 4.6
- Qwen2.5-VL 72B Instruct vs GLM-5.3
- Qwen2.5-VL 72B Instruct vs Muse Spark 1.3
- Qwen2.5-VL 72B Instruct vs DeepSeek V4 Pro
Other Alibaba (Qwen) models
- Qwen3.8 Max56.8
- Qwen3.7 Max51.5
- Qwen3.6 Max Preview51.5
- Qwen3.6 Plus47.5
- Qwen3.5 397B-A17B46.0
- Qwen3.8 27B46.0
- Qwen3.5 Max Preview45.3
- Qwen3.7 Plus45.3
Frequently asked questions
How good is Qwen2.5-VL 72B Instruct?
Qwen2.5-VL 72B Instruct by Alibaba (Qwen) ranks 302nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.9. Its strongest category is multimodal, where it ranks 97th. API pricing starts at $2.80 per million input tokens and $8.40 per million output tokens, with a 131K-token context window.
How much does Qwen2.5-VL 72B Instruct cost?
Qwen2.5-VL 72B Instruct costs $2.80 per million input tokens and $8.40 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen2.5-VL 72B Instruct's context window?
Qwen2.5-VL 72B Instruct accepts up to 131K tokens of input and can write up to 8K tokens in one response.
Is Qwen2.5-VL 72B Instruct open source?
Yes. Qwen2.5-VL 72B Instruct's weights are downloadable from Hugging Face (Qwen/Qwen2.5-VL-72B-Instruct); check the license for commercial terms.
How fast is Qwen2.5-VL 72B Instruct?
Qwen2.5-VL 72B Instruct generated about 43 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Qwen2.5-VL 72B Instruct's strengths and weaknesses?
Relative to other ranked models, Qwen2.5-VL 72B Instruct places best in reasoning and lowest in agentic & tool use.
What is Qwen2.5-VL 72B Instruct best at?
Its best category is multimodal, where it ranks 97th on Noometry.