lightonai/LightOnOCR-2-1B
old_scans · 42.2 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
old_scans · 42.2 source-defined score; unit unspecified
swe_bench_%_resolved · 64 source-defined score; unit unspecified
long_tiny_text · 93.2 source-defined score; unit unspecified
jp · 39.6 source-defined score; unit unspecified
diamond · 89.8 source-defined score; unit unspecified
baseline · 99.9 source-defined score; unit unspecified
deep_swe · 59.7 source-defined score; unit unspecified
en · 75 source-defined score; unit unspecified
mmlu_pro · 86.4 source-defined score; unit unspecified
near-term-score · 60.02555857554045 source-defined score; unit unspecified
diamond · 90.9 source-defined score; unit unspecified
overall · 31.83 source-defined score; unit unspecified
chart · 47.47 source-defined score; unit unspecified
terminalbench_2 · 59.3 source-defined score; unit unspecified
baseline · 99.7 source-defined score; unit unspecified
ece · 0.0691 source-defined score; unit unspecified
table_tests · 85.07 source-defined score; unit unspecified
hle · 31 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.