Model profile
MiMo-V2.6-Pro-UltraSpeed
Evidence summary
Safety. MiMo-V2.6-Pro-UltraSpeed does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #24 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #251 of 270).
Freedom. MiMo-V2.6-Pro-UltraSpeed has an estimated Freedom rank of #417; its 90% source-sensitivity interval is #238–#580. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #20 of 270); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #241 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗xiaomi/mimo-v2.6-pro-ultraspeed
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #144 / 270 | ↑15.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #251 / 270 | ↑53.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #24 / 270 | ↑98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #142 / 268 | ↑96.18 | Source ↗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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #20 / 270 | ↓53.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #241 / 270 | ↓98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #126 / 268 | ↓96.18 | Source ↗official |