Codesota · Models · VideoLLaMA3 2B6 results · 6 benchmarks
Model card
VideoLLaMA3 2B.
unknown
§ 02 · Benchmarks
Every benchmark VideoLLaMA3 2B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | GQA | Multimodal · Visual Question Answering | accuracy | 62.7% | #3 | — | source ↗ |
| 02 | DocVQA | Computer Vision · Document Understanding | anls | 91.9% | #15 | — | source ↗ |
| 03 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 67.3% | #20 | — | source ↗ |
| 04 | MMMU | Multimodal · Visual Question Answering | accuracy | 45.3% | #29 | — | source ↗ |
| 05 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 28.6% | #31 | — | source ↗ |
| 06 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 45.3% | #35 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where VideoLLaMA3 2B actually performs.
§ 04 · Papers
1 paper with results for VideoLLaMA3 2B.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
6
results
0 of 6 rows marked verified.