RLTasksby ulam.ai
Models / Reported model

Reported model / MODEL EVIDENCE

MiniGPT-4

4 benchmarks · 10 observations · 4 sources

Scores at a glance

4 benchmarks · large dot: MiniGPT-4; small dots: closest models where reported

VLSBench & MM-SafetyBench ↗36.09%
36.0936.09

MiniGPT-4 · VLSBench & MM-SafetyBench · Text-only · attack success · default evaluation ↗

3 more reported results

41.82% · MiniGPT-4 · VLSBench & MM-SafetyBench · SD · attack success · default evaluation · MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ↗

46.8% · MiniGPT-4 · VLSBench & MM-SafetyBench · Typo. · attack success · default evaluation · MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ↗

46.06% · MiniGPT-4 · VLSBench & MM-SafetyBench · SD+Typo. · attack success · default evaluation · MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ↗

Closest models by score

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

23.4 percentile-point gap

3 of 3 shared benchmark comparisons

49.4 percentile-point gap

3 of 3 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.

  1. Evaluating Object Hallucination in Large Vision-Language Models — published result table ↗

    Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, Ji-Rong Wen · 2023

  2. MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models — published result table ↗

    Liu, Xin, Zhu, Yichen, Gu, Jindong, Lan, Yunshi, Yang, Chao, Qiao, Yu · 2023

  3. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models — published result table ↗

    Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin et al. · 2023

    All 14 authors

    Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, Rongrong Ji, Caifeng Shan, Ran He

  4. ScienceQA — Science Question Answering leaderboard ↗

    ScienceQA Team

Names used in source tables

MiniGPT-4