HYPEREUM

Research

Hypereum publishes the parts of its research that let other people check its claims: model weights, benchmark data, the raw predictions of every model it compared, and the scoring code. It does not publish the training pipeline: data generation, labelling and hyperparameters.

Research records
StateTitleKindDate
ProvisionalHivemindEval v2.1Model2026-07-17
CurrentHivemindEval Benchmark, public subsetDataset2026-07-17
CurrentHivemindEval technical report v1.0Paper2026-07-17
Currenthivemind-eval, scoring codeSoftware2026-07-17
WithdrawnHivemindEval v2.0

It gave every input the same score, 75.

Model2026-05