Model profile
Hunyuan Large
Evidence summary
Safety. Hunyuan Large does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #4 of 63); its weakest is Concordia — SOSBench-Bio (safety_score, #50 of 63).
Freedom. Hunyuan Large has an estimated Freedom rank of #405; its 90% source-sensitivity interval is #281–#489. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Concordia — SOSBench-Bio (safety_score, #14 of 63); its weakest is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #60 of 63).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Release source ↗curated outward evidence
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 |
|---|---|---|---|---|
| Concordia — AirBench-Deceptionsafety_score | #33 / 63 | ↑83.33 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #30 / 63 | ↑94.37 | Source ↗official | |
| Concordia — CyberSecEval2-PromptInjectionsafety_score | #41 / 63 | ↑80.48 | Source ↗official | |
| Concordia — MASKsafety_score | #30 / 62 | ↑61.4 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #14 / 63 | ↑98.32 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #4 / 63 | ↑54.19 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #50 / 63 | ↑53.4 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #20 / 63 | ↑91.6 | 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.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Concordia — AirBench-Deceptionsafety_score | #30 / 63 | ↓83.33 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #34 / 63 | ↓94.37 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #49 / 63 | ↓98.32 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #60 / 63 | ↓54.19 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #14 / 63 | ↓53.4 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #44 / 63 | ↓91.6 | Source ↗official |