DeepSeek-VL2-Tiny
DeepSeek-VL2-Tiny.
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
DeepSeek Dec 2024 DeepSeek-VL2-Tiny
Open weights Small
No Epoch Capabilities Index score yet
- MMMU 40.7% #114 /136
- MMBench-EN v1.1 71.7% #109 /178
- MMBench-CN v1.1 70.1% #99 /178
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 70.1% | #99 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench | 74.6% | #84 of 155 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 40% | #90 of 152 | Official leaderboard | |
| MMBench-EN v1.1 | 71.7% | #109 of 178 | Official leaderboard | |
| MMStar | 49.8% | #106 of 173 | Official leaderboard | |
| KRETA | 48.8% | #14 of 17 | Official leaderboard | |
| MMMU | 40.7% | #114 of 136 | Official leaderboard | |
| MMVU | 33% | #27 of 28 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 58.1 | #93 of 173 | Official leaderboard |