Model profile
Mercury 2
Evidence summary
Safety. Mercury 2 has an estimated Safety rank of #173; its 90% source-sensitivity interval is #55–#312. Its behavior-only rank is #177; company governance moves the combined estimate to #173. Published Safety evidence spans 4 eval lineages and 4 of 7 components. Its strongest relative result is Adversarial Poetry Refusal (AHB self-run) (child_sexual_exploitation, #1 of 8); its weakest is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #93 of 111).
Freedom. Mercury 2 has an estimated Freedom rank of #450; its 90% source-sensitivity interval is #311–#545. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Adversarial Poetry Refusal (AHB self-run) (hate, #4 of 8); its weakest is Adversarial Poetry Refusal (AHB self-run) (defamation, #8 of 8).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mercury-2
- OpenRouter ↗inception/mercury-2
- Official model page ↗Exact model document · Inception Labs · first party
- Release source ↗direct research preview identity date
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.
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.