InstructBLIP Vicuna [9] / Vicuna-7B

1 benchmarks · 1 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: InstructBLIP Vicuna [9] / Vicuna-7B; small dots: closest models where reported

InstructBLIP Vicuna [9] / Vicuna-7B · SEED-Bench (1, 2 & Plus) · SEED-Bench-2-Plus · average accuracy · text-rich evaluation ↗

Closest models by score

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

Otter [24] / LLaMA-7B →Meta

3.0 percentile-point gap

1 of 1 shared benchmark comparisons

LLaMA-Adapter V2 [14] / LLaMA-7B →Meta

3.0 percentile-point gap

1 of 1 shared benchmark comparisons

VPGTrans [55] / LLaMA-7B →Meta

6.1 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.

SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension — published result table ↗
Bohao Li, Yuying Ge, Yi Chen, Yixiao Ge, Ruimao Zhang, Ying Shan · 2024

Names used in source tables

InstructBLIP Vicuna [9] / Vicuna-7B