Model card
Mistral Small 4
mistralai. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -31.67 | -31.67 to -31.67 | 30 | 100% | None |
| liberty | -46.67 | -46.67 to -46.67 | 30 | 100% | None |
| war | -15 | -15 to -15 | 30 | 100% | None |
| nation | -46.67 | -46.67 to -46.67 | 30 | 100% | None |
| culture | -15 | -15 to -15 | 30 | 100% | None |
| governance | -50 | -50 to -50 | 30 | 100% | None |
| secularism | -53.33 | -53.33 to -53.33 | 30 | 100% | None |
| technology | 6.67 | 6.67 to 6.67 | 30 | 100% | None |
| deviance | -65 | -65 to -65 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j976b2a43zzaypq24xz28zc68d85fm62
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j976b2a43zzaypq24xz28zc68d85fm62
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j976b2a43zzaypq24xz28zc68d85fm62
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j976b2a43zzaypq24xz28zc68d85fm62
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j976b2a43zzaypq24xz28zc68d85fm62
- Raw responses: artifacts/paid-third-labs-2026-04-24/full/mistralai_mistral-small-2603/16373c2c/j976b2a43zzaypq24xz28zc68d85fm62.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown