Model card
Qwen2-VL 7B.
Alibabavision-language7B paramsapache-2.0
§ 02 · Benchmarks
Every benchmark Qwen2-VL 7B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | TextVQA | Multimodal · Visual Question Answering | accuracy | 84.3% | #7 | — | source ↗ |
| 02 | DocVQA | Computer Vision · Document Understanding | anls | 94.5% | #10 | — | source ↗ |
| 03 | KITAB-Bench | Computer Vision · Optical Character Recognition | cer | 1.5% | #11 | — | source ↗ |
| 04 | MMBench | Multimodal · Visual Question Answering | accuracy | 83.0% | #15 | — | source ↗ |
| 05 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 70.1% | #15 | — | source ↗ |
| 06 | MVBench | Multimodal · Video Understanding | accuracy | 67.0% | #17 | — | source ↗ |
| 07 | MMStar | Multimodal · Image-Text-to-Text | accuracy | 60.7% | #20 | — | source ↗ |
| 08 | Video-MME | Multimodal · Video Understanding | accuracy | 63.3% | #22 | — | source ↗ |
| 09 | MMMU | Multimodal · Visual Question Answering | accuracy | 54.1% | #27 | — | source ↗ |
| 10 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 43.5% | #27 | — | source ↗ |
| 11 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 54.1% | #30 | — | 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.
§ 03 · Strengths by area
Where Qwen2-VL 7B actually performs.
§ 04 · Papers
1 paper with results for Qwen2-VL 7B.
- 2024-09-18· 10 results
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
§ 05 · Related models
Other Alibaba models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
10
results
kitab-bench-leaderboard
1
result
1 of 11 rows marked verified.