← Models

Model profile

Minicpm3 4B

2024-09-03release date
1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is DSPSafeBench (score, #3 of 12); its weakest is DSPSafeBench (score, #3 of 12).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionBetterSource
DSPSafeBenchscore#3 / 1277.64↑ higherSource ↗official