llava-v1.5-7b
llava-v1.5-7b.
Released 5 Oct 2023
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Oct 2023
llava-v1.5-7b
No Epoch Capabilities Index score yet
- A-Bench 65.6% #95 /116
- VCR (Visual Caption Restoration) 10.4% #37 /42
- MMBench-EN v1.1 62.3% #154 /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 | 43.9% | #169 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceQA | 66.8% | #16 of 23 | Epoch AI | |
| MMBench | 66.5% | #126 of 155 | Official leaderboard | |
| A-Bench | 65.6% | #95 of 116 | Official leaderboard | |
| LongVideoBench | 40.4% | #11 of 13 | Official leaderboard | |
| MMBench-EN v1.1 | 62.3% | #154 of 178 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 10.4% | #37 of 42 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 17.8% | #141 of 152 | Official leaderboard | |
| MMStar | 33.1% | #166 of 173 | Official leaderboard | |
| MATH-Vision (MathVision) | 8.52% | #105 of 105 | Official leaderboard | |
| BLINK | 38% | #11 of 11 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 36.9 | #165 of 173 | Official leaderboard |