Codesota · Models · EVA-02-LBAAI1 results · 1 benchmarks
Model card

EVA-02-L.

BAAIopen-sourceUnknown paramsEVA-02 Large + Cascade Mask R-CNN

Pre-trained with masked image-text modeling. 62.3 mAP on COCO val. CVPR 2024.

§ 01 · Benchmarks

Every benchmark EVA-02-L has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01COCOComputer Vision · Object DetectionmAP62.3%#8/13source ↗
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.
§ 02 · Strengths by area

Where EVA-02-L actually performs.

Computer Vision
1
benchmark
avg rank #8.0
§ 04 · Related models

Other BAAI models scored on Codesota.

EVA-02 (ViT-L/14+)
304M params · 1 result
EVA-02-L (LVIS)
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
1
result
0 of 1 rows marked verified.