PaddlePaddle/PaddleOCR-VL-1.6
table · 67.77 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
table · 67.77 source-defined score; unit unspecified
en · 84.5 source-defined score; unit unspecified
prompt_level_loose · 80.61 source-defined score; unit unspecified
text_content · 88.34 source-defined score; unit unspecified
photographed · 51.1 source-defined score; unit unspecified
gsm8k · 92.6 source-defined score; unit unspecified
latin · 81.7 source-defined score; unit unspecified
mmlu_pro · 85 source-defined score; unit unspecified
layout · 77.8 source-defined score; unit unspecified
ar · 1.3 source-defined score; unit unspecified
SWE_Bench_Pro · 50.4 source-defined score; unit unspecified
zh_t · 64.2 source-defined score; unit unspecified
SWE_Bench_Pro · 47.5 source-defined score; unit unspecified
auroc · 0.991 source-defined score; unit unspecified
lexam_hard · 37.55 source-defined score; unit unspecified
precision · 99.01 source-defined score; unit unspecified
ko · 80.3 source-defined score; unit unspecified
ale-cli-pass-rate · 19.047619047619047 source-defined score; unit unspecified
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.