PLM-3B

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning2 results

Video Question AnsweringonTVBench
Average Accuracy· 2025-04-17
58.9
best: 63.6 (Seed1.5-VL thinking)
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding arXiv:2504.13180
Video Question AnsweringonNExT-QA
Accuracy· 2025-04-17
83.4
best: 85.5 (LinVT-Qwen2-VL (7B))
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding arXiv:2504.13180