Benchmark Almanac

SmolVLM2-500M-Video-Instruct

SmolVLM2-500M-Video-Instruct.

Hugging Face Released February 11th, 2025 Family SmolVLM2 The lab's model card Compare with others
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Hugging Face Feb 2025

SmolVLM2-500M-Video-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • MM-Vet 29.9% #155 /164
  • SEED-Bench-2-Plus 47.7% #110 /136
  • A-Bench 61.2% #109 /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

BenchmarkScoreRankSource
MMBench-CN v1.1 33.4% #171 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
SEED-Bench-2-Plus 47.7% #110 of 136 Official leaderboard
MMStar 38.2% #153 of 173 Official leaderboard
MMBench-Video 1.01 #26 of 28 Official leaderboard
A-Bench 61.2% #109 of 116 Official leaderboard
CCBench (MMBench Chinese Culture) 13.3% #143 of 152 Official leaderboard
MM-Vet 29.9% #155 of 164 Official leaderboard
MMBench 53.1% #147 of 155 Official leaderboard
MMBench-EN v1.1 49.8% #170 of 178 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 40.9 #158 of 173 Official leaderboard