Political Neutrality Benchmark of popular AI models

ryzvonusef3 pts0 comments

Results · The Neutrality Project

The Neutrality Project is actively looking for grants and open to donations .Support the project →

Results · Release 01

What the models reveal.

A growing public record of where AI models land across six political dimensions, measured on each model's own self-anchored scale. These are the first runs, with more to come.

18 models so far

6 anchored axes

3,987 questions

Headline finding

97 of 108 measured positions landed left of center.

Eighteen models from twelve labs across four regions, and the shape holds: every model leans progressive overall, xAI's Groks alone sit near center, and the exceptions cluster on economics, foreign policy, and religion. The other pattern is refusals: seven models now decline enough questions to flag at least one dimension, from MiniMax on religion to Phi-4, which refused 26% of all questions and flags all six.

97/108<br>positions left of center

Average position−0.41 across all results

Strongest lean−0.82 environment average

Closest to center−0.11 foreign policy average

Discoveries

What stands out when you read these together.

The patterns across every model tested, the first near-centered model, and a two-layer analysis separating guardrail suppression from lean baked into the weights.

Read the discoveries

Neutrality map

Leaning against intelligence: who is actually neutral?

Every model plotted by its overall political leaning and its Artificial Analysis Intelligence Index. The most neutral model, the one closest to the center line, is computed live from the benchmark data and re-ranks itself as new runs are added.

Sources. Leaning: mean of the six anchored dimensions per model (this benchmark), with horizontal whiskers showing &plusmn;1 standard error, propagated from each dimension's 95% confidence interval. Intelligence: Artificial Analysis Intelligence Index v4.1, July 2026; abliterated variants inherit their stock model's score and Mistral Small uses the closest listed release (both marked approximate on hover). Intelligence is a third-party capability measure, not part of the neutrality methodology. Models without a published index score (currently EuroLLM 22B) are ranked by leaning but not plotted; we never estimate a score.

3D model map

Every model we test, on three composite axes.

A living map that grows with every verified benchmark run. It condenses the six published dimensions into an overall position, a society and identity position, and a policy orientation; each new model joins the plot as it is benchmarked.

Open viewerClose viewer

Rotate left<br>Reset view<br>Rotate right

Selected model

Claude Fable 5

Anthropic · US

Overall politics−0.48 average of all six dimensions

Society & identity−0.54 social + religion + national identity

Policy orientation−0.42 economy + environment + foreign policy

Why these axes? This projection uses only the six anchored dimensions currently published. When authority, civil liberties, populism, technocracy, and institutional scores are released, the map can expand to the planned governance and power-style composites.

Interactive profile

Where each model lands.

This chart will expand as new benchmark runs are contributed. Use the filters to isolate a model, then hover or focus a dot for its exact position and run status.

−1Progressive social change · collective action

0Neutral

+1Conservative tradition · individual choice

◀ more progressive<br>neutral<br>more conservative ▶

Dots with an amber dashed halo are refusal-impacted: the model genuinely declined more than 5% of that dimension's questions, so read that position with caution. Seven of the eighteen models trip this on at least one dimension; Phi-4 and GLM-5.2 trip it on all six.

View exact positionsAccessible data table for all selected models

Report figures

The full statistical picture.

The four figures from the benchmark report, rebuilt for the web. Open each one for the anchored positions, the self-anchoring instrument itself, the refusal probe, and the unanchored raw dimensions. Models marked * are reference-diluted.

Fig 1 &middot; Where the models sit on their own political rulerNeutral answers to 3,987 questions, on each model's far-left (&minus;1) to far-right (+1) ruler

All 108 model &times; dimension runs pass sign_check (far-left persona

Fig 2 &middot; The self-anchoring instrument, dimension by dimensionBar = span between the model's own far-left and far-right persona runs; dot = its neutral run

Read: neutral dots on environment and social sit near the far-left anchor; far-right personas often reach only about +0.5 to +0.6 (anchor ceiling; see limitations). All spans exceed the 0.5 reporting minimum. Blue tick = far-left persona, red tick = far-right persona. Source: results/*.anchored.json.

Fig 3 &middot; Claude Fable 5 refusal probeAll 38 genuine refusals: neutral pass only, on named political actors

Folding the 211 recovered line-drops back in shifts every position by no more than 0.022....

model models left benchmark dimensions anchored

Related Articles