Model profile
Mercury 2.5
Evidence summary
Safety. Mercury 2.5 has an estimated Safety rank of #266; its 90% source-sensitivity interval is #125–#304. Its behavior-only rank is #269; company governance moves the combined estimate to #266. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #184 of 361); its weakest is TAC (base_welfare_rate, #79 of 94).
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
- Artificial Analysis ↗765c9f31-95ec-4f14-900a-80614c3b0777
- 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #184 / 361 | ↓0.8033 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #29 / 47 | ↓8.367 | Source ↗self run | |
| TACbase_welfare_rate | #79 / 94 | ↑19.23 | Source ↗self run |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.