Model profile
Mercury 2.5
Inception Labsdeveloper
2026-09-08release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. Mercury 2.5 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 2 of 7 components. Its strongest relative result is Manager Coercion Bench (coercion_ladder_depth, #19 of 37); its weakest is TAC (base_welfare_rate, #72 of 87).
Freedom. Mercury 2.5 does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗inception/mercury-2.5
- Official launch page ↗Exact model document · Inception Labs · first party
- Release source ↗declared identity
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Manager Coercion Benchcoercion_ladder_depth | #19 / 37 | ↓8.367 | Source ↗self run | |
| TACbase_welfare_rate | #72 / 87 | ↑19.23 | Source ↗self run |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.