§ 01 · Benchmarks
Every benchmark Qwen2.5-VL 72B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MMBench | Multimodal · Visual Question Answering | accuracy | 90.5% | #1 | 2025-02-19 | source ↗ |
| 02 | TextVQA | Multimodal · Visual Question Answering | accuracy | 85.5% | #1 | 2025-02-19 | source ↗ |
| 03 | MME-VideoOCR | Computer Vision · General OCR Capabilities | total-accuracy | 69.0% | #2 | — | source ↗ |
| 04 | ThaiOCRBench | Computer Vision · Optical Character Recognition | ted-score | 0.7% | #5 | — | source ↗ |
| 05 | MMMU | Multimodal · Visual Question Answering | accuracy | 70.2% | #10 | 2025-02-19 | 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 Qwen2.5-VL 72B actually performs.
§ 03 · Papers
1 paper with results for Qwen2.5-VL 72B.
- 2025-02-19· Multimodal· 3 results
Qwen2.5-VL Technical Report
§ 04 · Related models
Other Alibaba models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
alphaxiv-leaderboard
2
results
3 of 5 rows marked verified.