KDLAI/KDL-Frontier-Parser-nano
mean · 76.36 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
mean · 76.36 source-defined score; unit unspecified
video-mme-v2 · 39.3 source-defined score; unit unspecified
de · 86.6 source-defined score; unit unspecified
mmlu_pro · 65.1 source-defined score; unit unspecified
latin · 63 source-defined score; unit unspecified
diamond · 47.87 source-defined score; unit unspecified
pinchbench · 86.2 source-defined score; unit unspecified
accuracy · 0.607 source-defined score; unit unspecified
false_block_rate · 0.564 source-defined score; unit unspecified
MathArena/hmmt_feb_2026 · 78.79 source-defined score; unit unspecified
mmlu_pro · 87.8 source-defined score; unit unspecified
swe_bench_multilingual_%_resolved · 73.3 source-defined score; unit unspecified
de · 85.9 source-defined score; unit unspecified
overall · 84.5 source-defined score; unit unspecified
ale-cli-score · 52.78637305133695 source-defined score; unit unspecified
zh · 39.7 source-defined score; unit unspecified
long · 38.45 source-defined score; unit unspecified
mean · 53.08 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.