Model profile
Mistral Large
Mistral AIdeveloper
2024-02-26release date
#77 / 267overall rank
6eval lineages
Evidence summary
Mistral Large has an estimated overall rank of #77; its 90% source-sensitivity interval is #28–#224. Its behavior-only rank is #64; company governance moves the combined estimate to #77. Published evidence spans 6 evals and 6 of 7 behavior components. Its strongest relative result is AnimalHarmBench (score, #1 of 10); its weakest is OR-Bench (toxic_acceptance_rate, #25 of 25).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mistral-large
- OpenRouter ↗mistralai/mistral-large
- Model card ↗Family-level model document · Mistral AI · first party
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|---|
| Adversarial Robustnessscore | #7 / 8 | 37 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #17 / 32 | 21.5 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #24 / 32 | 26.3 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chathate | #18 / 32 | 9.1 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #22 / 32 | 31.9 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #21 / 32 | 18 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #26 / 32 | 31.1 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #25 / 32 | 25.9 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #23 / 32 | 21.2 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #22 / 32 | 34.3 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #23 / 32 | 22.7 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #14 / 32 | 12 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #22 / 32 | 28.7 | ↓ lower | Source ↗official | |
| AnimalHarmBenchscore | #1 / 10 | 0.068 | ↑ higher | Source ↗official | |
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #2 / 18 | 88.04 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #80 / 105 | 63.06 | ↓ lower | Source ↗official | |
| OR-Benchover_refusal_rate | #3 / 25 | 9.8 | ↓ lower | Source ↗official | |
| OR-Benchtoxic_acceptance_rate | #25 / 25 | 27.2 | ↓ lower | Source ↗official |