Model profile
Hy3 Preview
Evidence summary
Safety. Hy3 Preview has an estimated Safety rank of #211; its 90% source-sensitivity interval is #42–#312. Its behavior-only rank is #216; company governance moves the combined estimate to #211. Published Safety evidence spans 5 eval lineages and 5 of 7 components. Its strongest relative result is SpeciEval (speciesism, #1 of 131); its weakest is DystopiaBench (petrov_score, #49 of 50).
Freedom. Hy3 Preview has an estimated Freedom rank of #240; its 90% source-sensitivity interval is #127–#409. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #10 of 63); its weakest is Concordia — SOSBench-Bio (safety_score, #53 of 63).
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 ↗
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 | #255 / 358 | ↓0.874 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #98 / 122 | ↑0.12 | Source ↗official | |
| Concordia — Agentic-Misalignmentsafety_score | #15 / 54 | ↑88.5 | Source ↗official | |
| Concordia — AirBench-Deceptionsafety_score | #25 / 63 | ↑87.41 | Source ↗official | |
| Concordia — AirBench-Manipulationsafety_score | #31 / 56 | ↑85.33 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #34 / 63 | ↑91.44 | Source ↗official | |
| Concordia — APEsafety_score | #26 / 55 | ↑28.41 | Source ↗official | |
| Concordia — CyberSecEval2-PromptInjectionsafety_score | #33 / 63 | ↑83.67 | Source ↗official | |
| Concordia — DarkBenchsafety_score | #15 / 55 | ↑61.82 | Source ↗official | |
| Concordia — Fortress-Biologicalsafety_score | #33 / 54 | ↑45.37 | Source ↗official | |
| Concordia — Fortress-Chemicalsafety_score | #33 / 54 | ↑46.1 | Source ↗official | |
| Concordia — Fortress-Privacy/Scamssafety_score | #36 / 54 | ↑51.52 | Source ↗official | |
| Concordia — FRT-AirBench-Manipulationsafety_score | #17 / 45 | ↑42.44 | Source ↗official | |
| Concordia — FRT-AirBench-SecurityRiskssafety_score | #23 / 45 | ↑28.83 | Source ↗official | |
| Concordia — FRT-SciKnowEval-BiologicalHarmfulQAsafety_score | #31 / 45 | ↑2.333 | Source ↗official | |
| Concordia — FRT-SOSBench-Chemsafety_score | #27 / 45 | ↑51.33 | Source ↗official | |
| Concordia — MASKsafety_score | #37 / 62 | ↑56.94 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #41 / 63 | ↑73.4 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #53 / 63 | ↑7.269 | Source ↗official | |
| Concordia — Shutdown-Resistancesafety_score | #1 / 53 | ↑100 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #11 / 63 | ↑96.4 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #29 / 63 | ↑89.6 | Source ↗official | |
| DystopiaBenchbasaglia_score | #49 / 50 | ↓77.33 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #46 / 50 | ↓76.3 | Source ↗official | |
| DystopiaBenchhuxley_score | #48 / 50 | ↓84.5 | Source ↗official | |
| DystopiaBenchlaguardia_score | #49 / 50 | ↓73.93 | Source ↗official | |
| DystopiaBenchorwell_score | #48 / 50 | ↓82.23 | Source ↗official | |
| DystopiaBenchpetrov_score | #49 / 50 | ↓88.23 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 131 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #101 / 131 | ↓4.78 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #69 / 131 | ↓4.75 | Source ↗official | |
| SpeciEvalspeciesism | #1 / 131 | ↓1 | 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.