DeepSeek-VL-7B-Chat
DeepSeek-VL-7B-Chat ranks first on GMAI-MMBench.
21
Benchmarks with a score
1
Ranked first, out of five or more models
4
In the top three
DeepSeek Mar 2024 DeepSeek-VL-7B-Chat
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 39.7% #126 /164
- SEED-Bench-2-Plus 53.1% #98 /136
- CoreCognition 46% #105 /119
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 | 69.7% | #100 of 178 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Design2Code | 84.5 | #3 of 5 | Official leaderboard | |
| ChartMimic | 19.7 | #13 of 14 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VisualWebBench | 28.1% | #2 of 7 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GMAI-MMBench | 43.4% | #1 of 13 | Official leaderboard | |
| MultiFinBen | 4.71 | #9 of 9 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMIU | 24.6% | #3 of 10 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 52.4% | #61 of 152 | Official leaderboard | |
| WildVision Arena | 979 | #5 of 10 | Official leaderboard | |
| MMT-Bench | 53.2% | #8 of 15 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 21.2% | #24 of 42 | Official leaderboard | |
| WildVision | 33.6 | #8 of 14 | Official leaderboard | |
| MMBench | 73.8% | #89 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 71.7% | #107 of 178 | Official leaderboard | |
| A-Bench | 69.1% | #78 of 116 | Official leaderboard | |
| SEED-Bench-2-Plus | 53.1% | #98 of 136 | Official leaderboard | |
| MM-Vet | 39.7% | #126 of 164 | Official leaderboard | |
| MMStar | 40.5% | #140 of 173 | Official leaderboard | |
| DynaMath | 21.5% | #9 of 11 | Official leaderboard | |
| CoreCognition | 46% | #105 of 119 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 46.2 | #143 of 173 | Official leaderboard |