Updated daily at 05:00 UTC
- Released
- Aug 2023
- Status
- Legacy
- Context
- 8.2K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- tongyi-qianwen
- Parameters
- 9.6B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| ScienceQA | Accuracy | 68.2% | Third party | — | — | VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks via Epoch AI |
| ScienceQA | Accuracy | 67.2% | Self-reported | — | — | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI |
Other Qwen-VL versions
- Qwen3-VL-2B-Instruct21 Oct 2025
- Qwen3-VL-2B-Thinking21 Oct 2025
- Qwen3-VL-32B-Instruct21 Oct 2025
- Qwen3-VL-32B-Thinking21 Oct 2025
- Qwen3-VL-4B-Instruct15 Oct 2025
- Qwen3-VL-4B-Thinking15 Oct 2025
- Qwen3-VL-8B-Instruct15 Oct 2025
- Qwen3-VL-8B-Thinking15 Oct 2025
- Qwen3-VL-Flash14 Oct 2025
- Qwen3-VL-30B-A3B-Instruct3 Oct 2025
- Qwen3-VL-30B-A3B-Thinking3 Oct 2025
- Qwen3-VL-235B-A22B-Instruct23 Sep 2025
- Qwen3-VL-235B-A22B-Thinking23 Sep 2025
- Qwen3-VL-Plus23 Sep 2025
- Qwen2.5-VL-32B-Instruct25 Mar 2025
- Qwen2.5-VL-3B-Instruct28 Jan 2025
- Qwen2.5-VL-72B-Instruct28 Jan 2025
- Qwen2.5-VL-7B-Instruct28 Jan 2025
- Qwen2-VL-72B-Instruct19 Sep 2024
- Qwen2-VL-2B-Instruct30 Aug 2024
- Qwen2-VL-7B-Instruct30 Aug 2024
- Qwen-VL-Max25 Jan 2024
- Qwen-VL-Plus25 Jan 2024