Skip to content

Benchmark

BLINK - Object_Localization

Vision benchmarks measure how well models understand images. Scores are percentages.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

46%
Mean
46.4%
Median
2.9%
Std dev
41.6%
10th percentile
49.6%
90th percentile
41.6%
Min
41.6%49.6%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen-VL MaxObject_Localization· EvalAI data49.6%
2Claude 3 OpusObject_Localization· EvalAI data46.4%
3Gemini ProObject_Localization· EvalAI data46.4%
4LLaVA 1.6 34BObject_Localization· EvalAI data41.6%