Model card
Qwen2-VL 72B.
Alibabaopen-sourceVision-Language Model1 current SOTA
Qwen2's large vision-language model.
§ 01 · Benchmarks
Every benchmark Qwen2-VL 72B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | VQA v2.0 | Multimodal · Visual Question Answering | accuracy | 87.6% | #1 | 2024-09-18 | source ↗ |
| 02 | CC-OCR | Computer Vision · General OCR Capabilities | kie-f1 | 71.8% | #1 | — | source ↗ |
| 03 | TextVQA | Multimodal · Visual Question Answering | accuracy | 84.9% | #2 | 2024-09-18 | source ↗ |
| 04 | CC-OCR | Computer Vision · General OCR Capabilities | document-parsing | 53.8% | #2 | — | source ↗ |
| 05 | CC-OCR | Computer Vision · General OCR Capabilities | multi-scene-f1 | 78.0% | #2 | — | source ↗ |
| 06 | MMBench | Multimodal · Visual Question Answering | accuracy | 88.0% | #3 | 2024-09-18 | source ↗ |
| 07 | CC-OCR | Computer Vision · General OCR Capabilities | multilingual-f1 | 71.1% | #3 | — | source ↗ |
| 08 | MMMU | Multimodal · Visual Question Answering | accuracy | 64.5% | #14 | 2024-09-18 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where Qwen2-VL 72B actually performs.
§ 03 · Papers
1 paper with results for Qwen2-VL 72B.
- 2024-09-18· Multimodal· 4 results
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
§ 04 · Related models
Other Alibaba models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
4
results
alphaxiv-leaderboard
2
results
cc-ocr-paper
2
results
6 of 8 rows marked verified.