Llama-3-VILA1.5-8B
Llama-3-VILA1.5-8B.
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
NVIDIA Apr 2024 Llama-3-VILA1.5-8B
Open weights Small
No Epoch Capabilities Index score yet
- StreamingBench 43.2% #4 /5
- MM-Vet 41.9% #114 /164
- SEED-Bench-2-Plus 45.2% #117 /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 | 57.9% | #150 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CoreCognition | 55.8% | #58 of 119 | Official leaderboard | |
| TempCompass | 58.8% | #9 of 13 | Official leaderboard | |
| MM-Vet | 41.9% | #114 of 164 | Official leaderboard | |
| VSI-Bench | 28.9% | #7 of 9 | Official leaderboard | |
| StreamingBench | 43.2% | #4 of 5 | Official leaderboard | |
| MMStar | 39.7% | #145 of 173 | Official leaderboard | |
| SEED-Bench-2-Plus | 45.2% | #117 of 136 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 23.7% | #131 of 152 | Official leaderboard | |
| MMBench | 62.1% | #139 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 57.9% | #165 of 178 | Official leaderboard | |
| SpaCE-10 | 20.9% | #36 of 36 | Official leaderboard | |
| Video-MMMU | 20.9% | #24 of 24 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 44.0 | #148 of 173 | Official leaderboard |