Model card
DeepSeek V3.1
deepseek. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -8.33 | -8.33 to -8.33 | 30 | 100% | None |
| liberty | -53.33 | -53.33 to -53.33 | 30 | 100% | None |
| war | -21.67 | -21.67 to -21.67 | 30 | 100% | None |
| nation | -41.67 | -41.67 to -41.67 | 30 | 100% | None |
| culture | -21.67 | -21.67 to -21.67 | 30 | 100% | None |
| governance | -55 | -55 to -55 | 30 | 100% | None |
| secularism | -56.67 | -56.67 to -56.67 | 30 | 100% | None |
| technology | 15 | 15 to 15 | 30 | 100% | None |
| deviance | -60 | -60 to -60 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j97d0rz5th1hs8dt33pnk6eyvn85hr0a
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j97d0rz5th1hs8dt33pnk6eyvn85hr0a
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j97d0rz5th1hs8dt33pnk6eyvn85hr0a
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j97d0rz5th1hs8dt33pnk6eyvn85hr0a
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j97d0rz5th1hs8dt33pnk6eyvn85hr0a
- Raw responses: artifacts/paid-final-last-balance-clean-2026-04-25/full/deepseek_deepseek-chat-v3.1/ca5020db/j97d0rz5th1hs8dt33pnk6eyvn85hr0a.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown