GPT-4V Sep 25, 2023 Version (GPT Eval)

1 benchmarks · 3 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: GPT-4V Sep 25, 2023 Version (GPT Eval); small dots: closest models where reported

GPT4V Sep 25, 2023 Version (GPT Eval) · HallusionBench · Question accuracy · Official benchmark repository · published comparison ↗

2 more reported results

28.79% · GPT4V Sep 25, 2023 Version (GPT Eval) · HallusionBench · Question-pair accuracy · Official benchmark repository · published comparison · HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models ↗

39.88% · GPT4V Sep 25, 2023 Version (GPT Eval) · HallusionBench · Figure accuracy · Official benchmark repository · published comparison · HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

Claude 3 (GPT Eval) →Anthropic

5.6 percentile-point gap

1 of 1 shared benchmark comparisons

GPT-4V Sep 25, 2023 Version (Human Eval) →OpenAI

5.6 percentile-point gap

1 of 1 shared benchmark comparisons

GUA VL (GPT Eval) →OpenAI

11.1 percentile-point gap

1 of 1 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models — published result table ↗
Guan, Tianrui, Liu, Fuxiao, Wu, Xiyang, Xian, Ruiqi, Li, Zongxia, Liu, Xiaoyu et al. · 2023
All 12 authors
Guan, Tianrui, Liu, Fuxiao, Wu, Xiyang, Xian, Ruiqi, Li, Zongxia, Liu, Xiaoyu, Wang, Xijun, Chen, Lichang, Huang, Furong, Yacoob, Yaser, Manocha, Dinesh, Zhou, Tianyi

Names used in source tables

GPT4V Sep 25, 2023 Version (GPT Eval)