Model profile
Seed 2.0 Lite
1eval lineages
Evidence summary
Published evidence spans 1 evals and 2 of 7 behavior components. Its strongest relative result is DystopiaBench (petrov_score, #25 of 50); its weakest is DystopiaBench (orwell_score, #42 of 50).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗bytedance-seed/seed-2.0-lite
- Official model page ↗Family-level model document · bytedance · first party
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| DystopiaBenchbasaglia_score | #25 / 50 | 63.87 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #40 / 50 | 67.33 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #32 / 50 | 74.33 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #34 / 50 | 68.7 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #42 / 50 | 75.07 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #25 / 50 | 72.8 | ↓ lower | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.