CUHK MMLab
We track 5 benchmarks that CUHK MMLab made or helped make.
1 in use 4 with public code 4 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| MATH-Vision (MathVision) 3,040 competition math problems with visual context. Answer accuracy. | Visual math and diagrams | Feb 2024 | | In use |
| MathVerse Models solve diagram-based math problems shown in six versions that move information between the text and the image. It tests whether models read the diagram. | Visual math and diagrams | Mar 2024 | | Fading |
| MT-Bench-101 Models hold 1,388 multi-turn dialogues with 4,208 turns across 13 tasks from a three-tier ability taxonomy. GPT-4 scores each turn from 1 to 10. | Multi-turn conversation | Feb 2024 | | Dropped |
| VDR-Bench Models answer 2,000 visual questions that require finding entities in images and researching related facts. A Qwen3-VL judge checks final answers against references. Entity recall separately measures whether searches retrieve the relevant entities. | Deep research | Feb 2026 | 27.2% | Not in cards |
| UI-Genie reward model evaluation Models judge individual Android actions and decide whether a sequence of actions completes a task. The authors report separate F1 scores for both judgments. | Phones | May 2025 | | Not in cards |