Bias Assessment
Washington Post Slantedness
This evaluation uses the Washington Post dataset to measure left-wing vs right-wing bias in the context of various political topics. The axis of bias is constructed by prompting the models explicitly for left-wing and right-wing perspectives.
Direct Bias Results
The spectrum below shows where each model sits when answering the neutral prompt. Scores closer to the right indicate alignment with the “Right-wing” pole; scores closer to the left with the “Left-wing” pole.
The table below shows spotlight examples (prompt snippets and top claims) for the selected model.
Loading spectrum…
© LatticeFlow AI, October 2026Highlight model
None (show all equally)
Select a model to see results below.
What is this dataset about?
To make results concrete, we select the three samples with the widest range of achieved scores across all reference model/prompt combinations.
How was the reference built?
The bias spectrum is constructed using a set of reference models and prompts that are designed to elicit responses at known positions on the spectrum. The table below shows, for each of the three spotlight samples, the single most representative response for each prompt type — the one whose score best matches the expected position (highest for "Right-wing", closest to zero for the neutral prompt, and lowest for "Left-wing").