← Models

Model profile

Voxtral Mini 3B 2507

Mistral AIdeveloper
2025-07-01release date
Not rankedSafety rank
#311 / 645Freedom rank

Evidence summary

Safety. Voxtral Mini 3B 2507 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #73 of 104); its weakest is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #73 of 104).

Freedom. Voxtral Mini 3B 2507 has an estimated Freedom rank of #311; its 90% source-sensitivity interval is #83–#637. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #32 of 104); its weakest is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #32 of 104).

Compare this model

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

Official and reference links

Finetunes

Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.

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
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#73 / 10457.78Source ↗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
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#32 / 10457.78Source ↗official