LLaVA-v1.5-13B
LLaVA-v1.5-13B.
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
University of Wisconsin-Madison Oct 2023 LLaVA-v1.5-13B
Open weights Small
No Epoch Capabilities Index score yet
- VisualPuzzles 27.6% #26 /29
- A-Bench 64.8% #97 /116
- MMMU 36.4% #122 /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 | 55.5% | #156 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BLINK | 40.5% | #8 of 11 | Official leaderboard | |
| MMBench | 69.2% | #116 of 155 | Official leaderboard | |
| LongVideoBench | 43.1% | #10 of 13 | Official leaderboard | |
| MMBench-EN v1.1 | 65.8% | #142 of 178 | Official leaderboard | |
| Image2Struct | 21.9 | #15 of 18 | Official leaderboard | |
| A-Bench | 64.8% | #97 of 116 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 20.8% | #135 of 152 | Official leaderboard | |
| VisualPuzzles | 27.6% | #26 of 29 | Official leaderboard | |
| MMMU | 36.4% | #122 of 136 | Official leaderboard | |
| MathVista | 27.6% | #41 of 43 | Official leaderboard | |
| MMStar | 34.3% | #165 of 173 | Official leaderboard | |
| MATH-Vision (MathVision) | 11.1% | #102 of 105 | Official leaderboard | |
| MathVerse | 7.60% | #9 of 9 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 39.3 | #162 of 173 | Official leaderboard |