SmolVLM2-2.2B-Instruct
SmolVLM2-2.2B-Instruct.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Hugging Face Feb 2025 SmolVLM2-2.2B-Instruct
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 34.9% #138 /164
- SEED-Bench-2-Plus 60.5% #76 /136
- A-Bench 73.8% #44 /116
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 | 53.2% | #160 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| A-Bench | 73.8% | #44 of 116 | Official leaderboard | |
| SEED-Bench-2-Plus | 60.5% | #76 of 136 | Official leaderboard | |
| MMBench-Video | 1.40 | #19 of 28 | Official leaderboard | |
| MMBench | 71.4% | #106 of 155 | Official leaderboard | |
| MMStar | 46% | #122 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 69.1% | #126 of 178 | Official leaderboard | |
| MM-Vet | 34.9% | #138 of 164 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 23.1% | #133 of 152 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 52.2 | #120 of 173 | Official leaderboard |