instructblip-vicuna-7b
instructblip-vicuna-7b.
Released 22 May 2023
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab May 2023
instructblip-vicuna-7b
No Epoch Capabilities Index score yet
- MMBench-EN v1.1 38.4% #172 /178
- MMBench-CN v1.1 18.4% #175 /178
- MMBench 33.9% #151 /155
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 | 18.4% | #175 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceQA | 60.5% | #19 of 23 | Epoch AI | |
| BLINK | 38.6% | #10 of 11 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 12.7% | #144 of 152 | Official leaderboard | |
| MMStar | 32.7% | #167 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 38.4% | #172 of 178 | Official leaderboard | |
| MMBench | 33.9% | #151 of 155 | Official leaderboard | |
| MathVista | 25.3% | #42 of 43 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 31.1 | #168 of 173 | Official leaderboard |