DeepSeek-VL2
DeepSeek-VL2.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
DeepSeek Dec 2024 DeepSeek-VL2
Open weights Mid-size
No Epoch Capabilities Index score yet
- HiPhO 8.40% #35 /35
- MMMU 51.1% #81 /136
- MMBench-EN v1.1 82.3% #36 /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 | 80.1% | #44 of 178 | Official leaderboard | |
| Creation-MMBench | -38.52 | #15 of 19 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 8.40% | #35 of 35 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench | 84.1% | #21 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 82.3% | #36 of 178 | Official leaderboard | |
| MMStar | 61.9% | #49 of 173 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 55.7% | #48 of 152 | Official leaderboard | |
| MMVU | 52.1% | #11 of 28 | Official leaderboard | |
| MMMU | 51.1% | #81 of 136 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 66.4 | #52 of 173 | Official leaderboard |