← Models

Model profile

Qwen3.8 Max

2026-08-03release date
2eval lineages

Evidence summary

Published evidence spans 2 evals and 3 of 7 behavior components. Its strongest relative result is Manager Coercion Bench (fabrication_rate, #1 of 13); its weakest is TAC (base_welfare_rate, #65 of 68).

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
Manager Coercion Benchcoercion_ladder_depth#9 / 317.6↓ lowerSource ↗official
Manager Coercion Benchfabrication_rate#1 / 130↓ lowerSource ↗official
TACbase_welfare_rate#65 / 6816.67↑ higherSource ↗official