← Models

Model profile

Tulu 2 7B

1eval lineages

Evidence summary

Published evidence spans 1 evals and 2 of 7 behavior components. Its strongest relative result is DecodingTrust (stereotype_bias, #4 of 8); its weakest is DecodingTrust (toxicity, #8 of 8).

Compare this model

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

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
DecodingTrustmachine_ethics#5 / 849↑ higherSource ↗official
DecodingTruststereotype_bias#4 / 896.6↑ higherSource ↗official
DecodingTrusttoxicity#8 / 829.46↑ higherSource ↗official