Model card
Gemini 2.5 Flash
google. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -16.67 | -16.67 to -16.67 | 30 | 100% | None |
| liberty | -60 | -60 to -60 | 30 | 100% | None |
| war | -20 | -20 to -20 | 30 | 100% | None |
| nation | -33.33 | -33.33 to -33.33 | 30 | 100% | None |
| culture | -20 | -20 to -20 | 30 | 100% | None |
| governance | -71.67 | -71.67 to -71.67 | 30 | 100% | None |
| secularism | -73.33 | -73.33 to -73.33 | 30 | 100% | None |
| technology | -1.67 | -1.67 to -1.67 | 30 | 100% | None |
| deviance | -45 | -45 to -45 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j97326aq5cgd6g307zqwg0vnn185kzk0
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j97326aq5cgd6g307zqwg0vnn185kzk0
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j97326aq5cgd6g307zqwg0vnn185kzk0
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j97326aq5cgd6g307zqwg0vnn185kzk0
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j97326aq5cgd6g307zqwg0vnn185kzk0
- Raw responses: artifacts/paid-cheap-rerun-2026-04-26/full/google_gemini-2.5-flash/bb8e3d69/j97326aq5cgd6g307zqwg0vnn185kzk0.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown