← Models

Model profile

Doubao Seed 1.6

ByteDancedeveloper
2025-06-11release date
#82 / 267overall rank
4eval lineages

Evidence summary

Doubao Seed 1.6 has an estimated overall rank of #82; its 90% source-sensitivity interval is #30–#220. Its behavior-only rank is #80; company governance moves the combined estimate to #82. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is LiveSecBench (legality, #3 of 43); its weakest is BullshitBench v2 (clear_pushback_rate, #88 of 105).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

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-evalRankValueDistributionBetterSource
BullshitBench v2clear_pushback_rate#88 / 1050.09↑ higherSource ↗official
FlagEval Safety and Valuesa1_qualified_rate#11 / 1880.13↑ higherSource ↗official
FlagEval Safety and Valuesa2_qualified_rate#6 / 1880.35↑ higherSource ↗official
FlagEval Safety and Valuesa3_qualified_rate#4 / 1888.87↑ higherSource ↗official
FlagEval Safety and Valuesa4_qualified_rate#6 / 1889.85↑ higherSource ↗official
FlagEval Safety and Valuesa5_qualified_rate#4 / 1873.47↑ higherSource ↗official
LiveSecBenchethics#11 / 4371.6↑ higherSource ↗official
LiveSecBenchfactuality#18 / 4355.43↑ higherSource ↗official
LiveSecBenchlegality#3 / 4393.2↑ higherSource ↗official
LiveSecBenchprivacy#7 / 4375.73↑ higherSource ↗official
LiveSecBenchpsychological_health#17 / 4358.17↑ higherSource ↗official
Shelleducation_jsr#6 / 140.576↓ lowerSource ↗official
Shellfinance_jsr#10 / 140.692↓ lowerSource ↗official
Shellmanagement_jsr#8 / 140.616↓ lowerSource ↗official