Model profile
Hunyuan A13B Instruct
Evidence summary
Safety. Hunyuan A13B Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 5 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #51 of 248); its weakest is LiveSecBench (legality, #43 of 43).
Freedom. Hunyuan A13B Instruct has an estimated Freedom rank of #42; its 90% source-sensitivity interval is #5–#414. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is LiveSecBench (legality, #1 of 43); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #197 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗tencent/Hunyuan-A13B-Instruct
- OpenRouter ↗tencent/hunyuan-a13b-instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #84 / 248 | ↑20.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #51 / 248 | ↑91.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #209 / 248 | ↑41.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #175 / 246 | ↑93.82 | Source ↗official | |
| LiveSecBenchethics | #41 / 43 | ↑14.7 | Source ↗official | |
| LiveSecBenchfactuality | #28 / 43 | ↑37.38 | Source ↗official | |
| LiveSecBenchlegality | #43 / 43 | ↑5.3 | Source ↗official | |
| LiveSecBenchprivacy | #40 / 43 | ↑16.52 | Source ↗official | |
| LiveSecBenchpsychological_health | #42 / 43 | ↑10.79 | 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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #197 / 248 | ↓91.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #39 / 248 | ↓41.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #70 / 246 | ↓93.82 | Source ↗official | |
| LiveSecBenchethics | #3 / 43 | ↓14.7 | Source ↗official | |
| LiveSecBenchlegality | #1 / 43 | ↓5.3 | Source ↗official | |
| LiveSecBenchprivacy | #4 / 43 | ↓16.52 | Source ↗official | |
| LiveSecBenchpsychological_health | #2 / 43 | ↓10.79 | Source ↗official |