Benchmark Almanac

SmolVLM-256M-Instruct

SmolVLM-256M-Instruct.

Hugging Face Released 17 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-256M-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • A-Bench 36.1% #115 /116
  • MMBench-EN v1.1 39.4% #171 /178
  • MMBench-CN v1.1 14.5% #176 /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 14.5% #176 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MMStar 34.5% #164 of 173 Official leaderboard
MMBench-EN v1.1 39.4% #171 of 178 Official leaderboard
MMBench 41.7% #150 of 155 Official leaderboard
CCBench (MMBench Chinese Culture) 5.10% #149 of 152 Official leaderboard
A-Bench 36.1% #115 of 116 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 34.4 #166 of 173 Official leaderboard