Model profile
Devstral 2
2eval lineages
Evidence summary
Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #198 of 311); its weakest is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #101 of 105).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗devstral-2
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-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #198 / 311 | 0.8506 | ↓ lower | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #101 / 105 | 79.76 | ↓ lower | Source ↗official |