EvalEval Coalition

@evaluatingevals

We are a researcher community developing scientifically grounded research outputs and robust deployment infrastructure for broader impact evaluations.

following
followers

Apertus 1.5 technical report is out, with evaluations claimed to be reproducible

A post lists 48 benchmarks for the 8B model and 47 for the 70B, inviting readers to rerun them.

2 Sources, 20d ago, first seen 20d ago

Eval Cards mapped to emerging AI governance requirements in California, the EU and the UK

The researchers say they mapped 40 requirements into 281 elements and identified 60 that belong in AI evaluation reporting.

2 Sources, 37d ago, first seen 37d ago

Featured in

Apertus 1.5 technical report is out, with evaluations claimed to be reproducible

Eval Cards mapped to emerging AI governance requirements in California, the EU and the UK

Featured in

Apertus 1.5 technical report is out, with evaluations claimed to be reproducible

Eval Cards mapped to emerging AI governance requirements in California, the EU and the UK