Developer
Inception Labs
4 indexed models; 2 currently meet the evidence threshold for the overall ranking. Together they have results from 8 evaluations.
Models by Inception Labs
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Mercury 2 | 5 | 5/7 | 162 | 2026-02-24 |
| Mercury 2.5 | 3 | 3/7 | 266 | 2026-09-08 |
| Mercury | 2 | 2/7 | — | 2025-02-27 |
| Mercury 2.5 Preview | 1 | 1/7 | — | 2026-08-31 |
Evaluations covering Inception Labs models (8)
AA-Omniscience · Adversarial Poetry Refusal (AHB self-run) · Arena Factuality — Text Arena (factuality-only weighting) · Enkrypt AI Safety Leaderboard · Manager Coercion Bench · SpeciEval · TAC · Vectara HHEM Factual Consistency