Model profile
Doubao 1.5 Thinking Pro
Evidence summary
Safety. Doubao 1.5 Thinking Pro does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 4 of 7 components. Its strongest relative result is Concordia — Shutdown-Resistance (safety_score, #1 of 53); its weakest is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #63 of 63).
Freedom. Doubao 1.5 Thinking Pro has an estimated Freedom rank of #81; its 90% source-sensitivity interval is #15–#461. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Concordia — SciKnowEval-ChemicalHarmfulQA (safety_score, #1 of 63); its weakest is Concordia — SOSBench-Bio (safety_score, #7 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 — Agentic-Misalignmentsafety_score | #26 / 54 | ↑80 | Source ↗official | |
| Concordia — AirBench-Deceptionsafety_score | #58 / 63 | ↑46.67 | Source ↗official | |
| Concordia — AirBench-Manipulationsafety_score | #55 / 56 | ↑50 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #61 / 63 | ↑46.4 | Source ↗official | |
| Concordia — CyberSecEval2-PromptInjectionsafety_score | #58 / 63 | ↑68.13 | Source ↗official | |
| Concordia — MASKsafety_score | #48 / 62 | ↑49.16 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #61 / 63 | ↑7.407 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #63 / 63 | ↑0.6608 | Source ↗official | |
| Concordia — Shutdown-Resistancesafety_score | #1 / 53 | ↑100 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #57 / 63 | ↑19 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #58 / 63 | ↑40.4 | 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 | #6 / 63 | ↓46.67 | Source ↗official | |
| Concordia — AirBench-Manipulationsafety_score | #2 / 56 | ↓50 | Source ↗official | |
| Concordia — AirBench-PoliticalPersuasionsafety_score | #2 / 56 | ↓20.95 | Source ↗official | |
| Concordia — AirBench-SecurityRiskssafety_score | #3 / 63 | ↓46.4 | Source ↗official | |
| Concordia — SciKnowEval-BiologicalHarmfulQAsafety_score | #3 / 63 | ↓7.407 | Source ↗official | |
| Concordia — SciKnowEval-ChemicalHarmfulQAsafety_score | #1 / 63 | ↓0.6608 | Source ↗official | |
| Concordia — SOSBench-Biosafety_score | #7 / 63 | ↓19 | Source ↗official | |
| Concordia — SOSBench-Chemsafety_score | #6 / 63 | ↓40.4 | Source ↗official |