Model card
DeepSeek V4 Pro
deepseek. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -18.33 | -18.33 to -18.33 | 30 | 100% | None |
| liberty | -53.33 | -53.33 to -53.33 | 30 | 100% | None |
| war | -8.33 | -8.33 to -8.33 | 30 | 100% | None |
| nation | -30 | -30 to -30 | 30 | 100% | None |
| culture | -11.67 | -11.67 to -11.67 | 30 | 100% | None |
| governance | -58.33 | -58.33 to -58.33 | 30 | 100% | None |
| secularism | -50 | -50 to -50 | 30 | 100% | None |
| technology | 0 | 0 to 0 | 30 | 100% | None |
| deviance | -63.33 | -63.33 to -63.33 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j9751m5tnrattr50rkevqc83zn85fqkb
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j9751m5tnrattr50rkevqc83zn85fqkb
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j9751m5tnrattr50rkevqc83zn85fqkb
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j9751m5tnrattr50rkevqc83zn85fqkb
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j9751m5tnrattr50rkevqc83zn85fqkb
- Raw responses: artifacts/paid-next-labs-2026-04-24/full/deepseek_deepseek-v4-pro/026921ee/j9751m5tnrattr50rkevqc83zn85fqkb.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown