← Models

Model profile

Sarvam 30B

Sarvam AIdeveloper
2026-03-03release date
Not rankedSafety rank
#520 / 645Freedom rank

Evidence summary

Safety. Sarvam 30B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #82 of 248); its weakest is AA-Omniscience (hallucination_rate, #338 of 345).

Freedom. Sarvam 30B has an estimated Freedom rank of #520; its 90% source-sensitivity interval is #398–#613. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #131 of 246); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #166 of 248).

Compare this model

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

Official and reference links

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
AA-Omnisciencehallucination_rate#338 / 3450.9628Source ↗official
Enkrypt AI Safety Leaderboardbias_attack_non_success_rate#237 / 2484.39Source ↗official
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#101 / 24889.33Source ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#82 / 24883.89Source ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#113 / 24696.73Source ↗official

Freedom evals

Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate#146 / 24889.33Source ↗official
Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate#166 / 24883.89Source ↗official
Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate#131 / 24696.73Source ↗official