Benchmark Almanac

Yi-VL-6B

Yi-VL-6B.

01.AI Released 25 Dec 2023 Family Yi-VL The lab's model card
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
01.AI Dec 2023

Yi-VL-6B

Open weights Small

No Epoch Capabilities Index score yet
  • OCRBench v2 19.7% #63 /65
  • A-Bench 69.8% #74 /116
  • VCR (Visual Caption Restoration) 4.70% #40 /42

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 63.1% #133 of 178 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
CCBench (MMBench Chinese Culture) 42.9% #83 of 152 Official leaderboard
BLINK 41.2% #7 of 11 Official leaderboard
A-Bench 69.8% #74 of 116 Official leaderboard
MMBench 68.4% #119 of 155 Official leaderboard
MMBench-EN v1.1 65.2% #144 of 178 Official leaderboard
MMMU 39.1% #117 of 136 Official leaderboard
MMStar 37.7% #155 of 173 Official leaderboard
VCR (Visual Caption Restoration) 4.70% #40 of 42 Official leaderboard
OCRBench v2 19.7% #63 of 65 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 41.1 #156 of 173 Official leaderboard