zai-org/GLM-5.1
prior_authorization · 18.7 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
prior_authorization · 18.7 source-defined score; unit unspecified
MathArena/hmmt_feb_2026 · 82.6 source-defined score; unit unspecified
vi · 69.2 source-defined score; unit unspecified
overall · 85.61 source-defined score; unit unspecified
MathArena/aime_2026 · 93.3 source-defined score; unit unspecified
swe_bench_%_resolved · 69.9 source-defined score; unit unspecified
diamond · 31.31 source-defined score; unit unspecified
hle · 55.4 source-defined score; unit unspecified
SWE_Bench_Pro · 61.7 source-defined score; unit unspecified
de · 72.4 source-defined score; unit unspecified
ko · 29.6 source-defined score; unit unspecified
main · 35.9375 source-defined score; unit unspecified
diamond · 74 source-defined score; unit unspecified
pass-rate-strict · 9.18 source-defined score; unit unspecified
swe_bench_%_resolved · 70.4 source-defined score; unit unspecified
latin · 86.5 source-defined score; unit unspecified
swebench · 0.5761 source-defined score; unit unspecified
SWE_Bench_Pro · 53.5 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.