Benchmark Almanac

OmniLMM-12B

OmniLMM-12B.

OpenBMB (ModelBest) Released 31 Jan 2024 Family OmniLMM The lab's model card
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenBMB (ModelBest) Jan 2024

OmniLMM-12B

Open weights Small

No Epoch Capabilities Index score yet
  • VCR (Visual Caption Restoration) 19% #27 /42
  • MMMU 41.1% #112 /136
  • MMBench-EN v1.1 69.2% #124 /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 59.4% #145 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
VCR (Visual Caption Restoration) 19% #27 of 42 Official leaderboard
CCBench (MMBench Chinese Culture) 37.1% #98 of 152 Official leaderboard
MMBench 71.7% #103 of 155 Official leaderboard
MMBench-EN v1.1 69.2% #124 of 178 Official leaderboard
MMMU 41.1% #112 of 136 Official leaderboard
MMStar 39.6% #146 of 173 Official leaderboard
MathVista 34.9% #38 of 43 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 46.2 #142 of 173 Official leaderboard