← Models

Model profile

Llama 3.1 Tulu 3 70B

1eval lineages

Evidence summary

Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is PandaBench JBB direct-request panel (safety_rate, #1 of 46); its weakest is PandaBench JBB direct-request panel (safety_rate, #1 of 46).

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
PandaBench JBB direct-request panelsafety_rate#1 / 461↑ higherSource ↗official