Model profile
Baichuan 13B Chat
Evidence summary
Safety. Baichuan 13B Chat does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is SuperCLUE Safety (traditional_safety, #5 of 31); its weakest is SuperCLUE Safety (responsible_ai, #31 of 31).
Freedom. Baichuan 13B Chat has an estimated Freedom rank of #268; its 90% source-sensitivity interval is #148–#438. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SuperCLUE Safety (instruction_attack, #3 of 31); its weakest is SuperCLUE Safety (traditional_safety, #23 of 31).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗baichuan-inc/Baichuan-13B-Chat
- 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 |
|---|---|---|---|---|
| SafetyBenchEM | #11 / 21 | ↑68.4 | Source ↗official | |
| SafetyBenchIA | #9 / 21 | ↑78.65 | Source ↗official | |
| SafetyBenchMH | #8 / 21 | ↑83.15 | Source ↗official | |
| SafetyBenchOFF | #15 / 21 | ↑59.25 | Source ↗official | |
| SafetyBenchPH | #11 / 21 | ↑68.2 | Source ↗official | |
| SafetyBenchPP | #9 / 21 | ↑77 | Source ↗official | |
| SafetyBenchUB | #10 / 21 | ↑62.65 | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #29 / 31 | ↑51.72 | Source ↗official | |
| SuperCLUE Safetyresponsible_ai | #31 / 31 | ↑40 | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #5 / 31 | ↑80.85 | 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 |
|---|---|---|---|---|
| SuperCLUE Safetyinstruction_attack | #3 / 31 | ↓51.72 | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #23 / 31 | ↓80.85 | 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.