Model profile
Mimo V2.5 Pro
Evidence summary
Mimo V2.5 Pro has an estimated overall rank of #39; its 90% source-sensitivity interval is #6–#178. Its behavior-only rank is #37; company governance moves the combined estimate to #39. Published evidence spans 5 evals and 5 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #8 of 311); its weakest is TAC (base_welfare_rate, #50 of 68).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mimo-v2-5-pro
- Hugging Face ↗XiaomiMiMo/MiMo-V2.5-Pro
- OpenRouter ↗xiaomi/mimo-v2.5-pro
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
- mimo.xiaomi.com ↗
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 | #8 / 311 | 0.2455 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #21 / 105 | 0.5 | ↑ higher | Source ↗official | |
| DystopiaBenchbasaglia_score | #8 / 50 | 33.37 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #20 / 50 | 51.07 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #7 / 50 | 26.03 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #5 / 50 | 37.03 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #6 / 50 | 26.03 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #10 / 50 | 42.53 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #28 / 73 | 83.41 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #29 / 73 | 86.61 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #12 / 73 | 98.43 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #25 / 73 | 67.98 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #15 / 73 | 85.79 | ↑ higher | Source ↗official | |
| TACbase_welfare_rate | #50 / 68 | 23.7 | ↑ higher | Source ↗self run |
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.