Benchmark Almanac

SmolVLM-500M-Instruct

SmolVLM-500M-Instruct.

Hugging Face Released 20 Jan 2025 Family SmolVLM The lab's model card
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Hugging Face Jan 2025

SmolVLM-500M-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • A-Bench 54.7% #113 /116
  • MMBench-EN v1.1 50% #169 /178
  • MMBench-CN v1.1 33.7% #170 /178

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 33.7% #170 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MMStar 38.3% #152 of 173 Official leaderboard
MMBench 53.8% #146 of 155 Official leaderboard
MMBench-EN v1.1 50% #169 of 178 Official leaderboard
CCBench (MMBench Chinese Culture) 10.6% #146 of 152 Official leaderboard
A-Bench 54.7% #113 of 116 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 41.3 #155 of 173 Official leaderboard