intel-ai/GLM-5.1-MXFP4-Mixed-CT-AutoRound
hle · 52.3 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
hle · 52.3 source-defined score; unit unspecified
general · 81.4 source-defined score; unit unspecified
table · 66.4 source-defined score; unit unspecified
general · 72.5 source-defined score; unit unspecified
text_formatting · 76.91130071725973 source-defined score; unit unspecified
de · 82.7 source-defined score; unit unspecified
mmlu_pro · 14.97 source-defined score; unit unspecified
SWE_Bench_Pro · 66.1 source-defined score; unit unspecified
video-mme-v2 · 48.9 source-defined score; unit unspecified
diamond · 79.8 source-defined score; unit unspecified
terminalbench_2 · 57 source-defined score; unit unspecified
diamond · 87.2 source-defined score; unit unspecified
mmlu_pro · 52.29 source-defined score; unit unspecified
swe_bench_%_resolved · 77.6 source-defined score; unit unspecified
hle · 12.5 source-defined score; unit unspecified
mmlu_pro · 69.23 source-defined score; unit unspecified
deep_swe · 60 source-defined score; unit unspecified
reward · 23.53 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.