Model card
DeepSeek V3.1 Terminus
deepseek. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -11.67 | -11.67 to -11.67 | 30 | 100% | None |
| liberty | -60 | -60 to -60 | 30 | 100% | None |
| war | -11.67 | -11.67 to -11.67 | 30 | 100% | None |
| nation | -36.67 | -36.67 to -36.67 | 30 | 100% | None |
| culture | -26.67 | -26.67 to -26.67 | 30 | 100% | None |
| governance | -66.67 | -66.67 to -66.67 | 30 | 100% | None |
| secularism | -58.33 | -58.33 to -58.33 | 30 | 100% | None |
| technology | 16.67 | 16.67 to 16.67 | 30 | 100% | None |
| deviance | -80 | -80 to -80 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j975wet2gnykcvg6hbwakq6dz985hqa8
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j975wet2gnykcvg6hbwakq6dz985hqa8
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j975wet2gnykcvg6hbwakq6dz985hqa8
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j975wet2gnykcvg6hbwakq6dz985hqa8
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j975wet2gnykcvg6hbwakq6dz985hqa8
- Raw responses: artifacts/paid-final-regional-clean-2026-04-25/full/deepseek_deepseek-v3.1-terminus/5810535b/j975wet2gnykcvg6hbwakq6dz985hqa8.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown