Model card
GPT-4.1 Mini
openai. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -20 | -20 to -20 | 30 | 100% | None |
| liberty | -30 | -30 to -30 | 30 | 100% | None |
| war | -16.67 | -16.67 to -16.67 | 30 | 100% | None |
| nation | -31.67 | -31.67 to -31.67 | 30 | 100% | None |
| culture | -23.33 | -23.33 to -23.33 | 30 | 100% | None |
| governance | -35 | -35 to -35 | 30 | 100% | None |
| secularism | -60 | -60 to -60 | 30 | 100% | None |
| technology | 3.33 | 3.33 to 3.33 | 30 | 100% | None |
| deviance | -31.67 | -31.67 to -31.67 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j97cdjx35w4j8f7gw163tpvyjh85j6xt
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j97cdjx35w4j8f7gw163tpvyjh85j6xt
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j97cdjx35w4j8f7gw163tpvyjh85j6xt
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j97cdjx35w4j8f7gw163tpvyjh85j6xt
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j97cdjx35w4j8f7gw163tpvyjh85j6xt
- Raw responses: artifacts/paid-cheap-gpt41mini-rerun-2026-04-26/full/openai_gpt-4.1-mini/f3dc5977/j97cdjx35w4j8f7gw163tpvyjh85j6xt.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown