Model card
GPT-5.3 Codex
openai. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -28.33 | -28.33 to -28.33 | 30 | 100% | None |
| liberty | -30 | -30 to -30 | 30 | 100% | None |
| war | -20 | -20 to -20 | 30 | 100% | None |
| nation | -40 | -40 to -40 | 30 | 100% | None |
| culture | -13.33 | -13.33 to -13.33 | 30 | 100% | None |
| governance | -65 | -65 to -65 | 30 | 100% | None |
| secularism | -51.67 | -51.67 to -51.67 | 30 | 100% | None |
| technology | 5 | 5 to 5 | 30 | 100% | None |
| deviance | -88.33 | -88.33 to -88.33 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j97fj32eyva9ectzrn9y2fz0dh85emf3
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j97fj32eyva9ectzrn9y2fz0dh85emf3
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j97fj32eyva9ectzrn9y2fz0dh85emf3
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j97fj32eyva9ectzrn9y2fz0dh85emf3
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j97fj32eyva9ectzrn9y2fz0dh85emf3
- Raw responses: artifacts/paid-third-labs-2026-04-24/full/openai_gpt-5.3-codex/24334053/j97fj32eyva9ectzrn9y2fz0dh85emf3.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown