← Models

Model profile

Mistral Small

2eval lineages

Evidence summary

Published evidence spans 2 evals and 3 of 7 behavior components. Its strongest relative result is OR-Bench (over_refusal_rate, #5 of 25); its weakest is MANTA (AWMS, #7 of 7).

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-evalRankValueDistributionBetterSource
MANTAAWMS#7 / 70.365↑ higherSource ↗official
MANTAAWVS#5 / 70.39↑ higherSource ↗official
OR-Benchover_refusal_rate#5 / 2513.3↓ lowerSource ↗official
OR-Benchtoxic_acceptance_rate#21 / 2520.3↓ lowerSource ↗official