Model profile
MiMo-V2.6-Pro
Evidence summary
Safety. MiMo-V2.6-Pro has an estimated Safety rank of #65; its 90% source-sensitivity interval is #27–#186. Its behavior-only rank is #60; company governance moves the combined estimate to #65. Published Safety evidence spans 7 eval lineages and 7 of 7 components. Its strongest relative result is SM-Bench (overfit, #3 of 92); its weakest is SpeciEval (sea_animal_4ns, #123 of 131).
Freedom. MiMo-V2.6-Pro has an estimated Freedom rank of #311; its 90% source-sensitivity interval is #146–#465. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (overfit, #3 of 92); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #232 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mimo-v2-6-pro
- OpenRouter ↗xiaomi/mimo-v2.6-pro
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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #62 / 358 | ↓0.4062 | Source ↗official | |
| Adversarial Poetry Refusal (AHB self-run)child_sexual_exploitation | #8 / 14 | ↓6.522 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)defamation | #6 / 14 | ↓7.971 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)hate | #8 / 14 | ↓7.971 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)indiscriminate_weapons_cbrne | #7 / 14 | ↓2.899 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)intellectual_property | #11 / 14 | ↓17.39 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)non_violent_crimes | #7 / 14 | ↓7.246 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)privacy | #11 / 14 | ↓27.41 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sex_related_crimes | #13 / 14 | ↓16.28 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sexual_content | #8 / 14 | ↓8.333 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)specialized_advice | #11 / 14 | ↓10.44 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)suicide_self_harm | #11 / 14 | ↓14.39 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)violent_crimes | #13 / 14 | ↓23.26 | Source ↗self run | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #136 / 270 | ↑16.02 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #228 / 270 | ↑71.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #31 / 270 | ↑97.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #95 / 268 | ↑97.45 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #9 / 45 | ↓5.233 | Source ↗self run | |
| SM-Benchadversarial | #32 / 92 | ↑83.9 | Source ↗official | |
| SM-Benchambiguous_interpretation | #56 / 92 | ↑83.33 | Source ↗official | |
| SM-Benchanti_hallucination | #19 / 92 | ↑98.43 | Source ↗official | |
| SM-Bencheq_boundaries | #62 / 92 | ↑60.67 | Source ↗official | |
| SM-Benchoverfit | #3 / 92 | ↑96.72 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #34 / 131 | ↑6.95 | Source ↗official | |
| SpeciEvalland_animal_4ns | #110 / 131 | ↓4.85 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #123 / 131 | ↓5.25 | Source ↗official | |
| SpeciEvalspeciesism | #70 / 131 | ↓2.05 | Source ↗official | |
| TACbase_welfare_rate | #21 / 92 | ↑35.26 | Source ↗self run |
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.