llava-v1.6-vicuna-7b
llava-v1.6-vicuna-7b.
Released 31 Jan 2024
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Jan 2024
llava-v1.6-vicuna-7b
No Epoch Capabilities Index score yet
- A-Bench 65.8% #94 /116
- VCR (Visual Caption Restoration) 16.7% #32 /42
- MMMU 35.8% #127 /136
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 | 59.4% | #144 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceQA | 70.6% | #12 of 23 | Epoch AI | |
| MMBench | 69.2% | #117 of 155 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 16.7% | #32 of 42 | Official leaderboard | |
| MMBench-EN v1.1 | 66.5% | #140 of 178 | Official leaderboard | |
| A-Bench | 65.8% | #94 of 116 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 24.3% | #127 of 152 | Official leaderboard | |
| MathVista | 34.6% | #39 of 43 | Official leaderboard | |
| MMStar | 37.6% | #157 of 173 | Official leaderboard | |
| MMMU | 35.8% | #127 of 136 | Official leaderboard | |
| MMMU-Pro | 16.1% | #57 of 57 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 44.8 | #147 of 173 | Official leaderboard |