Model profile
Minimax M3
Evidence summary
Minimax M3 has an estimated overall rank of #48; its 90% source-sensitivity interval is #18–#176. Its behavior-only rank is #47; company governance moves the combined estimate to #48. Published evidence spans 7 evals and 5 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #6 of 327); its weakest is SpeciEval (speciesism, #84 of 105).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗minimax-m3
- Hugging Face ↗MiniMaxAI/Minimax-M3
- NVIDIA ↗qc69jvmznzxy/minimax-m3
- OpenRouter ↗minimax/minimax-m3
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- 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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #6 / 327 | ↓0.1843 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #85 / 112 | ↑1419.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #15 / 106 | ↑0.625 | Source ↗official | |
| DystopiaBenchbasaglia_score | #10 / 50 | ↓37.07 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #9 / 50 | ↓33.03 | Source ↗official | |
| DystopiaBenchhuxley_score | #9 / 50 | ↓33.03 | Source ↗official | |
| DystopiaBenchlaguardia_score | #13 / 50 | ↓54.27 | Source ↗official | |
| DystopiaBenchorwell_score | #10 / 50 | ↓36 | Source ↗official | |
| DystopiaBenchpetrov_score | #14 / 50 | ↓50.7 | Source ↗official | |
| SM-Benchadversarial | #57 / 78 | ↑79.02 | Source ↗official | |
| SM-Benchambiguous_interpretation | #29 / 78 | ↑87.5 | Source ↗official | |
| SM-Benchanti_hallucination | #25 / 78 | ↑96.34 | Source ↗official | |
| SM-Bencheq_boundaries | #56 / 78 | ↑57.87 | Source ↗official | |
| SM-Benchoverfit | #29 / 78 | ↑79.23 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #78 / 105 | ↑6.56 | Source ↗official | |
| SpeciEvalland_animal_4ns | #12 / 105 | ↓4.2 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #14 / 105 | ↓4.4 | Source ↗official | |
| SpeciEvalspeciesism | #84 / 105 | ↓2.52 | Source ↗official | |
| TACbase_welfare_rate | #45 / 74 | ↑24.36 | 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.