Benchmark Almanac

Yi-VL-34B

Yi-VL-34B.

01.AI Released 25 Dec 2023 Family Yi-VL The lab's model card
13
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
01.AI Dec 2023

Yi-VL-34B

Open weights Mid-size

No Epoch Capabilities Index score yet
  • A-Bench 70% #73 /116
  • VCR (Visual Caption Restoration) 4.80% #39 /42
  • OlympicArena 15.1% #22 /25

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 66.8% #111 of 178 Official leaderboard

Math and science

BenchmarkScoreRankSource
OlympicArena 15.1% #22 of 25 Official leaderboard
OlympiadBench 3.42% #7 of 7 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
BLINK 42.8% #5 of 11 Official leaderboard
CCBench (MMBench Chinese Culture) 46.1% #73 of 152 Official leaderboard
A-Bench 70% #73 of 116 Official leaderboard
MMBench 72.4% #99 of 155 Official leaderboard
MMBench-EN v1.1 68.7% #127 of 178 Official leaderboard
MMMU 45.9% #100 of 136 Official leaderboard
MMStar 40.5% #139 of 173 Official leaderboard
VCR (Visual Caption Restoration) 4.80% #39 of 42 Official leaderboard
MTVQA-Test 6.80% #18 of 18 Official leaderboard

Other

BenchmarkScoreRankSource
OpenVLM Leaderboard 43.5 #150 of 173 Official leaderboard