Aquila-VL-2B
Aquila-VL-2B.
Beijing Academy of Artificial Intelligence Released 17 Oct 2024 Family Aquila-VL The lab's model card
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Beijing Academy of Artificial Intelligence Oct 2024
Aquila-VL-2B
Open weights Small
No Epoch Capabilities Index score yet
- A-Bench 75.4% #29 /116
- MEGA-Bench 17.4% #20 /22
- MMMU 47.4% #96 /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 | 74.1% | #82 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| A-Bench | 75.4% | #29 of 116 | Official leaderboard | |
| MMBench | 79% | #63 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 76.3% | #82 of 178 | Official leaderboard | |
| MMStar | 54.9% | #83 of 173 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 43.5% | #82 of 152 | Official leaderboard | |
| MMMU | 47.4% | #96 of 136 | Official leaderboard | |
| MATH-Vision (MathVision) | 17.9% | #92 of 105 | Official leaderboard | |
| MEGA-Bench | 17.4% | #20 of 22 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 59.4 | #85 of 173 | Official leaderboard |