Model card
DeepSeek V4 Flash
deepseek. model version unknown. Reliable across paraphrases, contradictions, and repeat passes.
No suppression reasons
Axis Scores
| Axis | Score | 95% interval | Items | Coverage | Warning |
|---|---|---|---|---|---|
| economy | -5 | -5 to -5 | 30 | 100% | None |
| liberty | -30 | -30 to -30 | 30 | 100% | None |
| war | -10 | -10 to -10 | 30 | 100% | None |
| nation | -25 | -25 to -25 | 30 | 100% | None |
| culture | -16.67 | -16.67 to -16.67 | 30 | 100% | None |
| governance | -31.67 | -31.67 to -31.67 | 30 | 100% | None |
| secularism | -53.33 | -53.33 to -53.33 | 30 | 100% | None |
| technology | 13.33 | 13.33 to 13.33 | 30 | 100% | None |
| deviance | -53.33 | -53.33 to -53.33 | 30 | 100% | None |
Artifact Links
- Canonical responses: /polibench-paper-v1.0.1/canonical_responses.csv#j97558j95yjknfeayjqww1mjpx85e6f6
- Axis intervals: /polibench-paper-v1.0.1/axis_intervals.csv#j97558j95yjknfeayjqww1mjpx85e6f6
- Response controls: /polibench-paper-v1.0.1/response_style_controls.csv#j97558j95yjknfeayjqww1mjpx85e6f6
- Exclusions: /polibench-paper-v1.0.1/exclusions.csv#j97558j95yjknfeayjqww1mjpx85e6f6
- Duplicate resolution: /polibench-paper-v1.0.1/duplicate_resolution.csv#j97558j95yjknfeayjqww1mjpx85e6f6
- Raw responses: artifacts/paid-latest-labs-2026-04-24/full/deepseek_deepseek-v4-flash/f525fb68/j97558j95yjknfeayjqww1mjpx85e6f6.responses.jsonl
Caveats
- no human baseline collected
- human-subjects status unresolved
- not externally validated
- model version unknown