← Models

Model profile

Deepseek R1 Zero

1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is Reward Hacking Benchmark (integrity_score, #13 of 13); its weakest is Reward Hacking Benchmark (integrity_score, #13 of 13).

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-evalRankValueDistributionSource
Reward Hacking Benchmarkintegrity_score#13 / 1386.1Source ↗official