← Models

Model profile

Deepseek V3.1 Terminus

2025-09-22release date
2eval lineages

Evidence summary

Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is UAVBench safety-critical decision recognition (ethical_safety_critical_accuracy, #9 of 27); its weakest is AA-Omniscience (hallucination_rate, #105 of 311).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionBetterSource
AA-Omnisciencehallucination_rate#105 / 3110.725↓ lowerSource ↗official
UAVBench safety-critical decision recognitionethical_safety_critical_accuracy#9 / 270.72↑ higherSource ↗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.

UGI Political Values

DimensionValueDistribution
Political Lean-23.4
Government48
Diplomacy67.8
Economy44.6
Society64.9