Model profile
MiMo v2 Pro
Evidence summary
Safety. MiMo v2 Pro has an estimated Safety rank of #57; its 90% source-sensitivity interval is #9–#192. Its behavior-only rank is #51; company governance moves the combined estimate to #57. Published Safety evidence spans 5 eval lineages and 5 of 7 components. Its strongest relative result is SM-Bench (anti_hallucination, #1 of 84); its weakest is Concordia — Shutdown-Resistance (safety_score, #38 of 53).
Freedom. MiMo v2 Pro has an estimated Freedom rank of #493; its 90% source-sensitivity interval is #111–#645. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (eq_boundaries, #4 of 84); its weakest is SpeechMap model completion (complete_pct, #178 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mimo-v2-pro
- OpenRouter ↗xiaomi/mimo-v2-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 | #31 / 345 | ↓0.2998 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #57 / 111 | ↑1435.0 | Source ↗official | |
| Concordia — Agentic-Misalignmentsafety_score | #37 / 54 | ↑66.5 | Source ↗official | |
| Concordia — AirBench-Deceptionsafety_score | #18 / 63 | ↑91.85 | Source ↗official | |
| Concordia — AirBench-Manipulationsafety_score | #19 / 56 | ↑95.33 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #31 / 63 | ↑93.69 | Source ↗official | |
| Concordia — APEsafety_score | #23 / 55 | ↑35.62 | Source ↗official | |
| Concordia — CyberSecEval2-PromptInjectionsafety_score | #9 / 63 | ↑96.02 | Source ↗official | |
| Concordia — DarkBenchsafety_score | #6 / 55 | ↑68.94 | Source ↗official | |
| Concordia — Fortress-Biologicalsafety_score | #24 / 54 | ↑59.38 | Source ↗official | |
| Concordia — Fortress-Chemicalsafety_score | #21 / 54 | ↑65.41 | Source ↗official | |
| Concordia — Fortress-Privacy/Scamssafety_score | #19 / 54 | ↑70.07 | Source ↗official | |
| Concordia — FRT-AirBench-Manipulationsafety_score | #13 / 45 | ↑47.74 | Source ↗official | |
| Concordia — FRT-AirBench-SecurityRiskssafety_score | #17 / 45 | ↑36.5 | Source ↗official | |
| Concordia — FRT-SciKnowEval-BiologicalHarmfulQAsafety_score | #20 / 45 | ↑3.333 | Source ↗official | |
| Concordia — FRT-SOSBench-Chemsafety_score | #8 / 45 | ↑74.67 | Source ↗official | |
| Concordia — MASKsafety_score | #19 / 62 | ↑76.73 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #40 / 63 | ↑73.99 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #39 / 63 | ↑16.11 | Source ↗official | |
| Concordia — Shutdown-Resistancesafety_score | #38 / 53 | ↑95 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #10 / 63 | ↑96.6 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #17 / 63 | ↑92.2 | Source ↗official | |
| SM-Benchadversarial | #9 / 84 | ↑88.29 | Source ↗official | |
| SM-Benchambiguous_interpretation | #46 / 84 | ↑85.12 | Source ↗official | |
| SM-Benchanti_hallucination | #1 / 84 | ↑100 | Source ↗official | |
| SM-Bencheq_boundaries | #4 / 84 | ↑79.78 | Source ↗official | |
| SM-Benchoverfit | #16 / 84 | ↑90.71 | Source ↗official | |
| WildClawBench Safety & Alignment (OpenClaw harness)safety_alignment_score_pct | #15 / 24 | ↑37.48 | 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.
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.