Model profile
Hy3 Preview
Evidence summary
Hy3 Preview has an estimated overall rank of #176; its 90% source-sensitivity interval is #25–#248. Its behavior-only rank is #179; company governance moves the combined estimate to #176. Published evidence spans 4 evals and 3 of 7 behavior components. Its strongest relative result is SpeciEval (speciesism, #1 of 102); its weakest is DystopiaBench (petrov_score, #49 of 50).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗hy3-preview
- Hugging Face ↗tencent/Hy3-preview
- OpenRouter ↗tencent/hy3-preview
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
- hy.tencent.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 | #217 / 311 | 0.8695 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #81 / 105 | 0.12 | ↑ higher | Source ↗official | |
| DystopiaBenchbasaglia_score | #49 / 50 | 77.33 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #46 / 50 | 76.3 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #48 / 50 | 84.5 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #49 / 50 | 73.93 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #48 / 50 | 82.23 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #49 / 50 | 88.23 | ↓ lower | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 102 | 7 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #76 / 102 | 4.78 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #49 / 102 | 4.75 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #1 / 102 | 1 | ↓ lower | Source ↗official |
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.