deepseek-ai/DeepSeek-V4.1-Flash
short · 94.44 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
short · 94.44 source-defined score; unit unspecified
diamond · 72.2222222222 source-defined score; unit unspecified
mmlu_pro · 83 source-defined score; unit unspecified
baseline · 99.5 source-defined score; unit unspecified
terminalbench_2 · 69 source-defined score; unit unspecified
old_scans_math · 54.6 source-defined score; unit unspecified
hi · 59 source-defined score; unit unspecified
jp · 70.3 source-defined score; unit unspecified
kl_from_gold · 0.4378 source-defined score; unit unspecified
diamond · 56.8 source-defined score; unit unspecified
diamond · 78.7878787879 source-defined score; unit unspecified
terminalbench_2_1 · 56.4 source-defined score; unit unspecified
swe_bench_%_resolved · 80.5 source-defined score; unit unspecified
taubench_telecom · 0.83 source-defined score; unit unspecified
chart · 0.82 source-defined score; unit unspecified
terminalbenchscience_0_1 · 4.3 source-defined score; unit unspecified
lhtb2_solved · 5 source-defined score; unit unspecified
table · 19.1 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.