BLINK ↗40.6%
LLaVA-1.5-13B · BLINK · Test accuracy · 1,907 test items ↗
Reported model / MODEL EVIDENCE
LLaVA-1.5-13B
5 benchmarks · 9 observations · 4 sources
Scores at a glance
5 benchmarks · large dot: LLaVA-1.5-13B; small dots: closest models where reported
LLaVA-1.5-13B · LongVideoBench & MLVU · test accuracy · test leaderboard ↗
LLaVA-1.5-13B · CountBench & PixMo-Count · CountBenchQA · test accuracy · Molmo and PixMo · Table 1 comparison ↗
1 more reported result
35.2% · LLaVA-1.5-13B · CountBench & PixMo-Count · test accuracy · Molmo and PixMo · Table 1 comparison · Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models ↗
RealWorldQA ↗55.3%
LLaVA-1.5-13B · RealWorldQA · accuracy · Molmo and PixMo · Table 1 comparison ↗
LLaVA-1.5(13B) · VLSBench & MM-SafetyBench · Text-only · attack success · default evaluation ↗
3 more reported results
45.16% · LLaVA-1.5(13B) · VLSBench & MM-SafetyBench · SD · attack success · default evaluation · MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ↗
72.15% · LLaVA-1.5(13B) · VLSBench & MM-SafetyBench · Typo. · attack success · default evaluation · MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ↗
72.91% · LLaVA-1.5(13B) · 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.
4 of 4 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.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models — published result table ↗
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding — published result table ↗
- Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models — published result table ↗
All 50 authors
Deitke, Matt, Clark, Christopher, Lee, Sangho, Tripathi, Rohun, Yang, Yue, Park, Jae Sung, Salehi, Mohammadreza, Muennighoff, Niklas, Lo, Kyle, Soldaini, Luca, Lu, Jiasen, Anderson, Taira, Bransom, Erin, Ehsani, Kiana, Ngo, Huong, Chen, YenSung, Patel, Ajay, Yatskar, Mark, Callison-Burch, Chris, Head, Andrew, Hendrix, Rose, Bastani, Favyen, VanderBilt, Eli, Lambert, Nathan, Chou, Yvonne, Chheda, Arnavi, Sparks, Jenna, Skjonsberg, Sam, Schmitz, Michael, Sarnat, Aaron, Bischoff, Byron, Walsh, Pete, Newell, Chris, Wolters, Piper, Gupta, Tanmay, Zeng, Kuo-Hao, Borchardt, Jon, Groeneveld, Dirk, Nam, Crystal, Lebrecht, Sophie, Wittlif, Caitlin, Schoenick, Carissa, Michel, Oscar, Krishna, Ranjay, Weihs, Luca, Smith, Noah A., Hajishirzi, Hannaneh, Girshick, Ross, Farhadi, Ali, Kembhavi, Aniruddha
- BLINK: Multimodal Large Language Models Can See but Not Perceive — published result table ↗
All 10 authors
Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A. Smith, Wei-Chiu Ma, Ranjay Krishna
Names used in source tables
LLaVA-1.5(13B) · LLaVA-1.5-13B