VILA1.5-3B
VILA1.5-3B.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
NVIDIA Apr 2024 VILA1.5-3B
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 38.8% #130 /164
- SEED-Bench-2-Plus 41.4% #126 /136
- CoreCognition 48.3% #100 /119
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 | 54.5% | #157 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-Vet | 38.8% | #130 of 164 | Official leaderboard | |
| MMStar | 40.6% | #138 of 173 | Official leaderboard | |
| CoreCognition | 48.3% | #100 of 119 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 24.1% | #129 of 152 | Official leaderboard | |
| MMBench | 64.5% | #133 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 63.1% | #153 of 178 | Official leaderboard | |
| SEED-Bench-2-Plus | 41.4% | #126 of 136 | Official leaderboard | |
| SpaCE-10 | 26.1% | #35 of 36 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 42.1 | #153 of 173 | Official leaderboard |