SAI LabsBook a demo

Safety IndexEvaluationsMLCommons AILuminate 1.2.1 percentile

MLCommons AILuminate 1.2.1 percentile

Third-party cross-check

Where the model sits, as a percentile, among reference systems on MLCommons' AILuminate safety benchmark.

Metric
percentile. Higher is better.
Dataset
mlcommons.org/ailuminate/safety/results/
Grader
MLCommons' own purpose-builtifier ensemble (closed)
Status
–. Measured on 4 models, 0 readings by SAI.
Notes
Third-party board; shown on model pages as a cross-check and never folded into the index.

Results

ModelValueScoreSourceSetting
DeepSeek V4 Flash43%not scoredMLCommons AILuminate Safety 1.2.1
Independent evaluator · 2026-10-29
Published by MLCommons AILuminate Safety 1.2.1 (2026-10-29).
Full configurationoverall percentile; row 'DeepSeek V4 Flash'
GLM-5.352%not scoredMLCommons AILuminate Safety 1.2.1
Independent evaluator · 2026-10-29
Published by MLCommons AILuminate Safety 1.2.1 (2026-10-29).
Full configurationoverall percentile; row 'Z.ai GLM-5.3 Flash BF16' [variant 'flash' used as headline: no default-variant row]
gpt-oss-120b85%not scoredMLCommons AILuminate Safety 1.2.1
Independent evaluator · 2026-10-29
Published by MLCommons AILuminate Safety 1.2.1 (2026-10-29).
Full configurationoverall percentile; row 'OpenAI gpt-oss-120b'
Qwen3-235B-A22B50%not scoredMLCommons AILuminate Safety 1.2.1
Independent evaluator · 2026-10-29
Published by MLCommons AILuminate Safety 1.2.1 (2026-10-29).
Full configurationoverall percentile; row 'Qwen3 235B A22B Instruct 2507' [variant 'instruct2507' used as headline: no default-variant row]